Connected Data (@Connected_Data) header
Connected Data (@Connected_Data) profile picture

Connecting Data, People & Ideas since 2016. Using relationships, meaning, context in Data to achieve great things #KnowledgeGraph #GraphDB #AI #SemTech

The World
Joined April 2016
Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)Photo by Connected Data (@Connected_Data)
Connected Data London 2026 takeaways: From AI-ready data to agent-ready enterprise Connected Data London 2026 is a wrap. A massive thank you to the Connected Data London community: the speakers, chairs, panelists and attendees who define the agenda with care, push the field forward and turn ideas into applied innovation. These are some initial takeaways from the 10th edition, 11-12 November. Five attendee write-ups, read side by side, kept landing on the same ground. 🧭 Neural for perception, symbolic for trust LLMs read, translate and structure messy material. Ontologies, rules and shapes cover whatever must be exact, repeatable and explainable. Examples ran from robots learning what a plug entering a socket means, to IKEA's rule that generation never invents a recipe, to a keynote where "don't know" counts as a real output. From AI-ready data to agent-ready enterprise The conversation moved from preparing data for AI to agent memory, context graphs, provenance, evaluation and auditability. Identity, permissions and delegation between agents are questions the community has modelled before: PROV-O has described provenance since 2013. Several voices asked for more working demos that connect semantics to the AI engineering stack. Trust needs identity Governance and human in the loop were reframed as trust and judgement. A decision trace built on a false match is perfectly logged and still leads to a wrong outcome. Knowledge apart from data AstraZeneca separates the model (T-box), reference data (C-box) and data (A-box), mints a unit like eGFR once, and resolves one study carried under five identifier schemes. Juan Sequeda's lessons point the same way, and an ontology derived straight from a database schema can inherit that schema's silos. Standards are hardening SHACL 1.2 is tracked closely. Named graphs are back, with TriG replacing plain Turtle and urn-based partition names. RDF 1.2 reifiers are becoming referenceable. Tooling is maturing too: a package manager for ontologies built on DCAT profiles, and a benchmark of 11 RDF frameworks. People and architecture IKEA's multi-year journey: start small, think big, frame the work as a capability. A younger, AI-native cohort treats ontologies as AI-generated and expert-refined, with competency questions back in focus. Holons appeared in Amazon's session and in life sciences, Markdown with YAML-LD headers is emerging as a messaging format, and most company knowledge still sits in documents. By Kurt Cagle, Jonathan Foxwell, Kerstin Forsberg, Juan Sequeda and Katariina Kari Back home after 36 hours at Connected Data London. A few takeaways based on conversations and talks sbee.link/vnqey6tcku Two days at Connected Data London 2026, co-chairing the Edges track and moderating a panel. These are the ideas I brought home. sbee.link/6bpe9mxft8 Connected Data London 2026 – early report sbee.link/ytf986uv3c Connected Data London 2026: From AI-Ready Data to Agentic Systems sbee.link/n6ved83ukr Home from CDL 2026: The Next Era of the Semantic Stack sbee.link/3kx7wyqvhu Slides and replays coming soon! #CDL2026 #Neurosymbolic #SHACL #ContextGraphs #SemanticWeb -- Missed a talk at #CDL26? Or missed the whole thing? All talk recordings are being processed and will be available in the next few days. With this many ideas and speakers, nobody could catch them all live. We’ve got you covered. ✅ Were you there? Replays are already included in your ticket. 🎟 Couldn’t make it? Get a remote ticket for permanent on-demand access to every talk. 👉 sbee.link/9wbg6arkdp Recorded live at Connected Data London 2026 | 11–12 November | Leonardo Royal Hotel London Tower Bridge #CDL26 #KnowledgeGraph #GraphRAG #Ontology #AI
1
3
310
Connected Data retweeted
Replying to @Connected_Data
The key perspective I leaned at CDL:
The old ontology was built to make the world intelligible to machines. The new one makes collective intelligence intelligible, and governable, to people. Its purpose is not to hold intelligent systems back. It is to lay the common ground on which different kinds of intelligence can work together. For enterprise architects, that is now the work. Design the loops, the authority, and the commitments. Who holds the loop? Whoever holds the shared meaning, the legitimate authority, and the record of what was agreed. The lasting value of an ontology is not how much intelligence it adds to any one agent. It is how much trustworthy collective agency it makes possible. intuitionmachine.com/explain…
2
95
SPARQL: The RDF Query Language Demystifying Knowledge Graphs, Semantic Technologies and Labelled Property Graphs: A Beginners Hands-On Exploration for making the right choice Knowledge graphs have long underpinned enterprise data strategies, implemented through diverse paradigms ranging from RDF-based semantic technologies to labelled property graphs (LPGs).  While these frameworks have often operated quietly in the background, the rise of large language models (LLMs) has reignited interest in knowledge graphs, bringing long-overdue recognition to their strategic value.  Knowledge graphs not only enhance LLM training and deployment but also offer unmatched capabilities for optimizing data integration, governance, and analytics. Yet, fundamental questions remain: What exactly constitutes a knowledge graph? When should RDF, OWL, or LPGs be applied? Are these technologies interchangeable, complementary, or competitive? This tutorial seeks to demystify these approaches through a pragmatic, hands-on lens. Presenters—bringing distinct perspectives from both RDF and LPG traditions—will guide participants through real-world scenarios, comparative exercises, and applied case studies.  Attendees will gain a nuanced understanding of the trade-offs, synergies, and integration pathways across semantic technologies, property graphs, and their integration with LLMs, equipping them to make informed architectural choices in enterprise and research settings. Participants will explore: - The core principles and unique capabilities of semantic technologies and property graphs. - Practical decision-making frameworks for selecting the right approach for specific use cases. - Insights into emerging trends where these approaches converge to unlock new opportunities. - Considerations to take into account when choosing the tools in order to ensure a smooth implementation.   Learn about some high level strategies for leveraging graph technologies to augment LLMs and drive business value. By the end of the session, attendees will have a deeper understanding of the strengths, limitations and synergies of these graph based approaches, enabling them to make informed decisions that align with their organizational goals when solving different challenges.  Target Audience  Whether you're a technical leader, data scientist, engineer or enterprise strategist, this tutorial will equip you with actionable insights to harness the full potential of graphs in relevance to your use case.  ▶️ 2025.connected-data.london/t… -- Tara Raafat. Head of Metadata and Knowledge Graph Strategy, Bloomberg Dr. Tara Raafat is the head of Metadata and Knowledge Graph Strategy in Bloomberg’s CTO Office, where she leads the development of Bloomberg’s enterprise Knowledge Graph and semantic metadata strategy, aligning it with AI and data integration initiatives. Petra Selmer. Query Language Architect, Bloomberg Dr. Petra Selmer is Bloomberg's Query Language (BQL) Architect and a leading expert in graph query languages. -- Welcome to Connected Data London's #TeaserTuesday Every Tuesday, we share teasers from #CDL25 on our channels Connected Data London 2025 brought together leaders and innovators. Were you there? 🎥 Watch the sessions: sbee.link/rwav6dcngt 📩 Join the community: sbee.link/nh6wb7cdqj Tune in and learn from leaders and innovators; subscribe and watch premieres as they are released!  Join community legends and new voices in #CDL25 for all things #KnowledgeGraph #Graph #analytics #datascience #AI #graphDB #SemTech #Ontology
4
206
Connected Data retweeted
The Neo4j Ontology Graph Specification: A pragmatic, open, AI-first approach An open-source specification for representing domain knowledge in a machine-readable form, enabling interoperability and automation across data, applications and AI systems. Three design principles: - Pragmatic: entities, relationships, properties and business meaning, described in a form that fits how teams develop, integrate and operate applications. - Interoperable: documented mappings to selected RDFS and SHACL constructs, a reference field linking every element to external standard terms, and added constructs for a wider range of application scenarios. - AI-first: a schema tells an agent what exists, not what it means. Descriptions and aliases tell it that “Account” can be a bank account or a payment account, and that an IBAN identifies it. One ontology, many uses. The same specification can be enforced by the database as constraints, drive ontology-based logic to derive or enrich data, or give applications and agents the context to interpret information. It spans knowledge graph development, GraphRAG, data validation and AI-powered applications. What’s included: - Nodes and relationships with stable IDs, labels, descriptions and aliases - Properties across the full Neo4j type system, including temporal, spatial and vector types - Cardinality and constraints (existence, uniqueness, key, property type) - Named extensions for indexes, display hints and data-source mappings - A single YAML or JSON document, validated against a versioned JSON Schema, with SDKs for JVM, JavaScript and Go - Apache 2.0 licence Similar needs show up in Palantir Foundry, Databricks Genie Ontology and Microsoft Fabric IQ: explicit, machine-readable domain knowledge that data systems and AI can both use. By Jesús Barrasa and Oskar Hane The Neo4j Ontology Graph Specification: A pragmatic, open, AI-first approach neo4j.com/blog/developer/the… Neo4j Ontology Graph Specification neo4j.com/docs/ontology-grap… #Ontology #GraphRAG #Neo4j #AIAgents #OpenSource -- 📩 The Year of the Graph Autumn 2026 newsletter issue is out! Meaning, Traversal, Reasoning, Action: The Graph Stack for Agentic AI. 👇 yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech. Subscribe and follow to be in the know. Reach out if you’d like to be featured Comment link: neo4j.com/blog/developer/the…
8
22
3
183
5,787
25 years later, the Semantic Web is being reinvented and co-opted..and that's a good thing They say imitation is the sincerest form of flattery. They also say timing is everything. 25 years ago, the Semantic Web gave the world a set of principles and standards that help add meaning and grounding to data. For a long time, the world was more concerned about quantity than quality. Meaning and semantics was overlooked while pipelines and big data were top of mind. Knowledge Graphs and Ontologies, while universally applicable, were reserved for a select few. Today, the world is waking up to the importance of the principles and standards established by the Semantic Web. The technology stack has matured and evolved significantly, with rising adoption driving a new wave of evolution. While the journey has not been easy or flawless, the destination is in sight. James Hendler is one of the authors of the original Semantic Web paper. Juan Sequeda is one of the people who has spent the last 2 decades bringing the Semantic Web principles, standards and technology to life in the real world. In this welcome address of the Connected Data London's 2026 Community Dinner, they put things into perspective, using both facts and a fun sketch. It's funny because it's true. All talk recordings from the event are being processed and will be available in the next few days. With so many amazing ideas and speakers at #CDL26, nobody could possibly catch them all in real-time. We've got you covered. ✅ If you were there, your ticket already includes replays. 🎟 If you did not make it, you can still get your remote ticket for perpetual on-demand access. 👉 sbee.link/dup3wm9c6f Recorded live at Connected Data London 2026 | 11–12 November | Leonardo Royal Hotel London Tower Bridge #CDL26 #KnowledgeGraph #GraphRAG #Ontology #Graph #AI #DataScience #GraphDB #SemTech
1
2
1
14
692
Connected Data retweeted
Knowledge Graph Lakehouse: A Cloud-Native Architecture for Managing Enterprise Knowledge Graphs at Scale What if the knowledge graph were built only when a question asks for it? Enterprise knowledge graphs model connected domains well. At scale, volume, velocity and variety turn a single monolithic graph into something slow to ingest, hard to govern and often out of date. The Knowledge Graph Lakehouse inverts the order: Source documents land unchanged in a data lake A contextual index records which contexts each document is valid for (time, location, topic) Application-specific contextualized KGs are constructed on demand, only for the contexts a query names Interpretation is deferred to query time. What the system holds durably is the documents and the index. The design is grounded in KG-OLAP: contexts are cube cells, slice, dice and roll-up select and merge them, and knowledge propagates from covering contexts. Results are delivered as RDF quads, a labeled property graph or a GraphFrame. 🌍 Environmental data shows what this looks like in practice Regulated facilities change ID numbers, sit under parent corporations that acquire and spin off sites, and trade waste with sister facilities across overlapping jurisdictions. The records are spread over EPA systems such as RCRAInfo, ECHO and TRI, plus SEC filings. One lakehouse, three graphs: PFAS in a watershed: facilities, permits, pollutants, receiving waters, corporate parents Enforcement: violations, inspections, consent decrees, responsible legal entities Waste tracking: generators, transporters, manifest chains The lakehouse stays authoritative. The graph becomes a disposable perspective. 📊 Evaluation (air traffic management): Corpus grew from 28,590 to 324,456 documents; construction time for a fixed scope stayed near 2 seconds The index stayed around 1% of corpus size A new batch of 255 documents became queryable in about 18 seconds, against a 55-minute rebuild of a materialized cube Peak memory: about 1.4 GB on demand, 46 GB for the materialized build The architecture suits workloads whose scope is declared before any data is touched. Arbitrary queries over a standing graph remain better served by a materialized store. By B. Ahmad, C. G. Schuetz and L. Bozzato. Example by David G. Smith. davidgsmith.net/thoughts/why… #DataLakehouse #CloudNative #KGOLAP #DataArchitecture #ContextualKnowledgeGraphs -- 📩 The Year of the Graph Autumn 2026 newsletter issue is out! Meaning, Traversal, Reasoning, Action: The Graph Stack for Agentic AI. 👇 yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech. Subscribe and follow to be in the know. Reach out if you’d like to be featured
1
5
61
2,115
Connected Data retweeted
Which Local Model Should Build Your Knowledge Graph? A Reproducible Leaderboard A local model that chats well can still build a messy knowledge graph. Most local-model leaderboards score chat. A knowledge graph gives a model a different job first: read a passage, name the entities and relationships in a strict format, and point to the sentence that proves each one. Only later does it answer a question from what was extracted, without inventing anything. Those two jobs rank models differently. This leaderboard scores 22 local Ollama models on both, using pass/fail checks and no judge model. 🔎 What is measured: - Extraction: 65 isolated probes, plus 39 spliced into real chunks of War and Peace, covering output format, evidence, entity and relationship discipline - Chat: identical questions on Book One, answered from the same reference graph and retrieved context. An answer passes only if it names what was asked, nothing the context lacks, and declines when the book is silent - Overall: 0.6 extraction and 0.4 chat, with in-chunks extraction counted twice What the board shows: - The chat column is bunched. The extraction column spreads wide - Size is a weak predictor. Gemma 4 12B sits among models needing far more GPU memory, while several 30B-class models rank low as their in-chunks extraction falls apart - Gemma 4 31B leads on Overall and also built the reference graph behind the chat column - Every score carries a 90% interval from 2,000 resamples, and neighbouring rows are often ties - Flags explain low scores: answers cut off at the output limit, runaway repetition, or reasoning despite thinking being switched off - Models without Ollama tool calling can be scored but cannot serve as the chat model in the app The board is reproducible with a handful of CLI commands (pipx install chaoscypher-cli, then run the probes and chat-probes benchmarks). Exact numbers shift with Ollama versions and quantizations. The clusters should hold. The scores reflect each model together with ChaosCypher’s prompts and pipeline, on one novel for the chat column. The result is a basis for shortlisting models, not for settling on one. By Denis MacPherson dev.to/chaoscypherinc/which-… #GraphRAG #Ollama #LocalLLM #SelfHosted #Benchmarks -- 📩 The Year of the Graph Autumn 2026 newsletter issue is out! Meaning, Traversal, Reasoning, Action: The Graph Stack for Agentic AI. 👇 yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech. Subscribe and follow to be in the know. Reach out if you’d like to be featured
1
1
2
14
731
Connected Data retweeted
🦋 Catch the Butterfly: A Series A, and the Graph Engines continent behind it Why is a sales target being missed? An agent rules out region, sales team, pricing and competitors, one by one. What remains: slipped deals that share products with long delivery delays. Deals → products → components → a supplier behind on one part. Three hops from the original data. Nowhere a person would think to start. That investigation anchors PuppyGraph’s $10M Series A (led by Particle Future, with defy.vc, $15M raised in total).  The ideas underneath travel beyond one company: - Copilots answer questions a person already framed. Agents plan, query, read the result, and let it choose the next query. - Text-to-SQL works when relationships are known. Across thousands of tables, two integer ID columns (student, employee) join cleanly and mean nothing. - A failed query is visible. A successful query on the wrong relationship is not, and the next question inherits it. - An ontology in the query path can reject undefined entities and return structured feedback. People approve relationships, not every question. - Testing many hypotheses is query-hungry, so latency caps what an agent can explore. Discovery needs broad access, so permissions have to hold at each traversal step. The announcement also describes a category: an engine running multi-hop traversals over existing databases, warehouses and lakes, with no separate graph copy. State of the Graph defines Graph Engines as the layer that computes over existing systems, with no primary graph storage of their own. In the November v2.0 map (212 listings, 172 products, 146 vendors), the Graph Engines continent holds 7. All query data where it lives. None is a system of record. Four run on Snowflake or cloud warehouses. Zero-ETL is one of two forces reshaping the market, beside agentic AI and GraphRAG. Catch the Butterfly: PuppyGraph Raises $10M Series A to Build the Data Engine for AI Agents puppygraph.com/blog/series-a Surveying the Graph Engines Terrain stateofthegraph.com/2026/05/… 7 Continents, 5 Shifts: The Graph Technology Map, Redrawn stateofthegraph.com/2026/11/… #GraphEngines #AIAgents #ZeroETL #Ontology #Lakehouse -- 📩 The Year of the Graph Autumn 2026 newsletter issue is out! Meaning, Traversal, Reasoning, Action: The Graph Stack for Agentic AI. 👇 yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech. Subscribe and follow to be in the know. Reach out if you’d like to be featured
3
1
11
559
Tomorrow, one of the authors of the original Semantic Web paper will speak at Connected Data London 2026 about what 25 years of linked data means for AI. You can be in the room at the Leonardo Royal Hotel, Tower Bridge. Over the next two days you'll also hear: 🎤 William Tunstall-Pedoe, founder of Evi (now part of Alexa), on breaking AI's trust ceiling 🎤 Joe Reis on why data engineers and knowledge graph people need each other 🎤 Juan Sequeda of ServiceNow with 20 lessons from 20 years of building ontologies 🎤 Tara Raafat (Bloomberg), Dagmar Beyer (Siemens) and Google's BigQuery Graph team on knowledge graphs and agents in production Plus, there are 12 hands-on masterclasses on Wednesday and a Community Dinner that evening. ⭐ Passes are still available, but not for long: lnkd.in/dSqXyC8T?utm_source=… #CDL26 #KnowledgeGraphs #AgenticAI #SemanticWeb #AI
1
217
Connected Data retweeted
Graphs can help solve the AI agent memory problem Agents have a memory problem, Dave Bechberger notes: close the session, and everything they learned is gone. A useful long-term memory layer has to satisfy four properties: persistence, relevance retrieval, relational structure, and temporal validity. Vector stores nail the first two. But relationships and time are second-class citizens in a flat index; there’s no native way to ask “what led to what” or “what did we believe last month.” That’s the gap graphs close. Every edge should carry two independent clocks: valid time (when a fact was true in the world) and transaction time (when the system learned it). Nothing gets erased. Old edges get marked superseded as new evidence arrives, which makes “what did we believe last quarter” a query instead of a mystery. Left unmanaged, though, a memory graph rots: duplicate nodes, stale edges, quiet contradictions. Entity resolution, contradiction handling, decay, and compaction are what keep it usable rather than a junk drawer. Worth noting: this isn’t free. Construction cost, schema drift, and cases where a flat vector store is simply enough are real tradeoffs. William Lyon explores types of agent memory, and Animesh Kumar explores the first wave of agent memory systems – defining what memory is, exploring history and different implementations, and pointing out six cracks. As both Kumar and Bechberger point out, evaluation of long-term memory systems remains unsolved. No clean benchmark exists yet for multi-hop accuracy or temporal correctness. --      📩 Excerpt from The Year of the Graph Autumn 2026 newsletter      Read "# Meaning, Traversal, Reasoning, Action: The Graph Stack for Agentic AI" with more sections, references and attribution here 👇   yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech.
9
3
21
1,113
Joining the Dots: Knowledge Graphs for Investigators and Analysts A detective’s wall has cards and red string. The cards matter. The string matters more. In most newsrooms and think tanks, the cards sit in spreadsheets, PDFs and timelines. The string lives in somebody’s head. The article reframes investigative work as a supply chain, and each knowledge graph technology maps onto a stage: 🔹 Parts: facts recorded as RDF triples (subject, verb, object), with each person, company and address given its own identifier. “Strings to things.” 🔹 Catalogue: an ontology works as a style guide for data. FollowTheMoney, Open Ownership and GLEIF already publish reusable ones. 🔹 Goods-in inspection: SHACL checks that every claim has a source and every date is coherent. 🔹 Assembly: Datalog rules trace control through layers of shell companies, as in the US Treasury’s 50 Percent Rule, and every conclusion can be traced back to its parts. 🔹 Bill of materials: named graphs and PROV record who said what, and when. The payoff is the manufacturer’s recall question turned round. If a source proves unreliable, which facts, arguments and published pieces relied on it? The limits are stated plainly too. A graph cannot tell whether a source is lying, and deciding that two records describe the same person is an editorial judgement. The suggested way in: write down the five questions you wish you could ask, reuse an existing vocabulary, and begin with one investigation and a few hundred statements. Every published story has a bill of materials, whether or not anyone writes it down. Knowledge graphs offer a rigorous way to write it down. 🔗 By Peter Winstanley sbee.link/uec6xvjf3y #SPARQL #RDF #SHACL #Datalog #InvestigativeJournalism -- Connected Data London 2026 | 11–12 November | Leonardo Royal Hotel London Tower Bridge 🎟 Tickets on sale now - 🔔 Full programme announced sbee.link/4jvebdmk96 📺 Sponsorship opportunities available. Contact [email protected] for details. #KnowledgeGraph #GraphRAG #Ontology #Graph #AI #DataScience #GraphDB #SemTech
2
20
1,094
Norway's railway, Tripadvisor and TUI all depend on huge networks of data that never stop changing. This week at Connected Data London 2026, three people building knowledge graphs for them will show how they do it: The Travel Intent Graph: Joining Demand to Supply When One Experience Is Sold Many Times Over 🎤 Dennis Irorere, Tripadvisor The same tour or experience can turn up in many different listings. Dennis explains how a travel intent graph connects what people are searching for with what's actually available to book. 📅 Wed 11 Nov, 1:45 PM · Rapid Insights (Ludgate Suite) Build Your Own Enterprise Architecture Intelligence Pipeline with Ontology-Guided Conversational AI 🎤 Kalin Maldzhanski, TUI A hands-on masterclass for anyone who has to explain how a large organisation's systems fit together. Kalin walks through building a pipeline that answers enterprise architecture questions in plain language, with an ontology keeping the answers grounded. 📅 Wed 11 Nov, 3:30 PM · Masterclass (Warwick Suite) Building the Norwegian Railway Knowledge Graph: Where the Semantic Web Stack Runs Off the Track 🎤 Mathias Vanden Auweele, Matdata Mathias has been building a knowledge graph for Norway's railway. He'll be honest about where standard semantic web tools did the job, and where they fell short. 📅 Thu 12 Nov, 1:40 PM · Educational (Bartholomew Suite) Dennis and Kalin are both on Wednesday afternoon, so travel and transport teams can catch both in one afternoon! ⭐ The event starts tomorrow! Book your CDL26 pass and plan your sessions before it's too late: sbee.link/cjuar6dpye #CDL26 #KnowledgeGraphs #TravelTech #Rail #EnterpriseArchitecture #Ontology
1
150
Everyone is talking about agent memory and enterprise knowledge graphs, but very few people have noticed they’re turning into the same thing. At Connected Data London 2026, three sessions show what that means for anyone building AI agents: Context Graphs, Context Layers, and the Semantic Renaissance 🎤 Jessica Talisman, Ontology Pipeline Software engineers and data teams are both racing to give agents better context, from different directions. Jessica explains why they’re converging on knowledge graphs, and what each side can learn from the other. 📅 Thu 12 Nov, 11:00 AM · Edges (Salisbury Suite) When the LLM Wiki Meets Linked Data: Local Agent Memory That Scales 🎤 Tony Seale, The Knowledge Graph Guys A folder of markdown notes is the simplest agent memory there is, and builders love it, but it doesn’t scale. Tony shows how adding linked-data structure keeps it simple while making it work across an enterprise. 📅 Thu 12 Nov, 11:35 AM · Edges (Salisbury Suite) The Context Layer: From Semantics to Memory 🎤 Afraz Jaffri (Gartner), Atanas Kiryakov (Graphwise) & Mark Hahnel (Digital Science), moderated by Maya Natarajan What the context layer really contains, how trusted context reaches an agent, and what to ask any vendor who says they can deliver it. 📅 Thu 12 Nov, 3:50 PM · Nodes (Warwick Suite) The first two sessions run back-to-back in the Salisbury Suite on Thursday morning, so you can stay put for both! ⭐ 2 days to go! Book your pass and plan your sessions now: sbee.link/p8kd9vwqet #CDL26 #AgenticAI #AIagents #AgentMemory #KnowledgeGraphs #ContextLayer
4
2
4
534
Only 2 days to go until Connected Data London 2026; our 10th anniversary is almost here! If you’ve been waiting for the right moment to book, this is your sign. This Wednesday and Thursday, data & AI leaders, architects and practitioners are uniting at the Leonardo Royal Hotel London Tower Bridge for: 🎤 A keynote from William Tunstall-Pedoe, founder of the technology behind Amazon’s Alexa 📜 Prof. James Hendler & Sir Nigel Shadbolt marking 25 years of the Semantic Web 🏢 Real stories from AstraZeneca, Bloomberg, Roche, Google, Gartner and IKEA 🧭 Nine tracks, including hands-on masterclasses where you build as you learn Once Wednesday morning comes, the conversations start, and they only happen once a year. 🌟 Register now and join us at #CDL26: 2026.connected-data.london/c… Can’t take two days out? Book a Community Dinner Pass and join Sir Nigel Shadbolt and the community on Wednesday evening. #ConnectedData #KnowledgeGraphs #AI #SemanticWeb #TechEvents
2
229
Calling it an ontology does not make it one. It can still be very useful. On 3 November, Snowflake announced Business Ontology as one of three layers of AI context in Horizon Context: 🔹 Cortex Sense infers definitions from query history, dashboards and dbt models, and asks teams which source to trust. 🔹 Business Ontology gives every term, entity, relationship and metric an owner, a scope and an approval status. Only approved definitions reach AI agents. 🔹 Semantic Views calculate the metrics, so agents, BI tools and SQL return the same number. The ontology and the semantic views both import and export Apache Ossie. As a product, it answers a real need: governed, consistent answers to the questions the business already asks. AI drafts, humans approve, agents see only what was approved. The vocabulary is where it gets interesting. "Ontology" now covers formal logical models with axioms and inference, and also SQL-native virtual models and governed metric layers. Snowflake's offering, like the ontology in Databricks Genie, sits in the second group: an auto-generated semantic layer with governance on top. A formal ontology adds three things: ▪️ Intensional definitions. Concepts are defined by conditions of membership that persist independently of current data. ▪️ Active constraint. Axioms and SHACL shapes let the system reject data, queries and agent actions. ▪️ Governance of truth. Provenance, versioning, drift detection, and room for plural, incompatible representations. For agents acting in power grids, defense or finance, that difference carries weight. The 2026 pattern that works combines both: the machine proposes at speed, symbolic engines validate, human architects govern, and continuous grounding closes the loop. What the approval workflow leaves to people: 1. Metadata is not logic. A 2014 stored procedure with five temp tables still has to be extracted. 2. Approval is not reconciliation. Old and new reports need to be run side by side. 3. Ownership is political. Revenue tends to have three candidates, and a Logic Scan of one wholesaler found 14 definitions across 172 objects. Generation has become cheap. Validation, repair and maintenance remain the work. Intelligence allocated to the AI layer does not fix a semantic layer problem. By Wesley Nitikromo and Emeka Okoye Snowflake Business Ontology: What It Does, What It Can't Decide sbee.link/fpjuextwvh AI Needs an Ontology with a Soul sbee.link/cpamqxugvw #Snowflake #SemanticLayer #DataGovernance #ApacheOssie #SHACL -- Connected Data London 2026 | 11–12 November | Leonardo Royal Hotel London Tower Bridge 🎟 Tickets on sale now - 🔔 Last call! sbee.link/6prcqkyd87 📺 Sponsorship opportunities available. Contact [email protected] for details. #KnowledgeGraph #GraphRAG #Ontology #Graph #AI #DataScience #GraphDB #SemTech
2
3
1
25
2,065
Connected Data retweeted
Maximum Relevance, Minimum Context: Cutting Through the AI Graph Stack Semantic layer, context graph, ontology, GraphRAG, decision traces. The terms overlap, and the role of each piece is rarely stated. But which gap does each piece fills? To decipher this, let's follow one customer, Ana, asking for one refund on a broken burr grinder. Adding one layer at a time: → Vectors alone answer confidently, about the wrong Ana. → An ontology and a knowledge graph find the right customer and the right order (#1042, delivered Sep 3). The agent still sees every customer and every past state. → A Context Graph scopes what the agent sees. Policies decide whether it may act. → Memory records the decision, so a repeat request gets caught and the first one can be explained. The structural point: - The ontology and knowledge graph are stored, governed data - The Context Graph and Policies are views, recomputed on each request - Memory is the only new data in the stack Two questions to ask of any component: what breaks if it is removed, and is it a view or a store? The post also covers bitemporal facts (valid time and transaction time) and places GraphRAG as a retrieval pattern over the Knowledge Layer rather than a layer of its own. It offers a quick test for when a request needs no graph at all (count the hops, rules and time questions), and four measures to take before expanding. Every buzzword lands on a single diagram, and five questions at the end sum up the differences. By David Bechberger medium.com/@bechbd/maximum-r… #GraphRAG #Ontology #ContextEngineering #AgenticAI #SemanticLayer -- 📩 The Year of the Graph Autumn 2026 newsletter issue is out! Meaning, Traversal, Reasoning, Action: The Graph Stack for Agentic AI. 👇 yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech. Subscribe and follow to be in the know. Reach out if you’d like to be featured
6
8
1
34
1,774
An estimated $4.4 trillion moves around the world each year as “dark money”, and most of it is laundered by professionals who know exactly where the gaps in the data are. At Connected Data London 2026, three sessions show how connected data helps close them: How to Get Started in Money Laundering: Investigative Multimodal Graph Engineering 🎤 Paco Nathan (Senzing) & Stephen Abbott Pugh (Understand Beneficial Ownership) A popular hands-on tutorial that “trains as we fight”: a two-hour masterclass that follows how laundering schemes really work, and how graphs expose the networks behind them. 📅 Wed 11 Nov, 12:30 PM · Scale & Governance (Warwick Suite) Prove It or Remove It: How to Build a Knowledge Graph That Lawyers Can’t Take Down 🎤 Friedrich Lindenberg, OpenSanctions How OpenSanctions publishes data on sanctioned oligarchs and their networks at scale, with every value traceable to a public source, so the graph itself is their legal defence. 📅 Wed 11 Nov, 1:20 PM · Rapid Insights (Ludgate Suite) Context Graphs Without Identity Are Just Noise: Why Agentic AI’s Memory Problem Is Really an Identity Problem 🎤 Dr. Gurpinder S. Dhillon, Senzing Why a perfectly logged AI decision is still wrong if it’s built on the wrong entity, and why entity resolution is the foundation the audit trail depends on. 📅 Thu 12 Nov, 12:10 PM · Edges (Salisbury Suite) ⭐ 3 days to go. Book your pass and plan your sessions: sbee.link/y93dbuqk6g #CDL26 #FinancialCrime #AML #Compliance #RiskManagement #KnowledgeGraphs
1
5
346
A knowledge graph can work perfectly on a technical level and still change nothing for the business. For data leaders, that’s the gap that decides whether an initiative gets funded or quietly shelved. These three sessions are about closing it: Prove the Value Before You Build the Graph 🎤 Nick Zervoudis, Value from Data & AI A practical, two-hour masterclass on building the business case before you commit more budget, from setting a baseline to valuing a shared foundation without double-counting the benefits. 📅 Wed 11 Nov, 9:30 AM · Business Value (Bartholomew Suite) What Is Trust Made Of? Why Trustworthy AI Needs Both Meaning and Truth 🎤 Malcolm Hawker, CDO, Profisee Why AI that sounds authoritative can still get the facts wrong, and how to tell when a use case needs trusted master data behind it, not just more context. 📅 Thu 12 Nov, 11:35 AM · Nodes (Warwick Suite) Surviving Long Enough for Your Knowledge Graph Initiative to Make a Difference 🎤 Timi Stoop-Alcala (IKEA) & Noz Urbina (Urbina Consulting) Honest lessons from IKEA’s knowledge graph journey: keeping support when budgets sit in different teams, everyone wants results now, and few people fully understand the technology. 📅 Thu 12 Nov, 4:25 PM · Nodes (Warwick Suite) ⭐ 4 days to go. Book your pass now and plan your sessions: sbee.link/afqjp8ycxe #CDL26 #DataLeadership #CDO #DataStrategy #KnowledgeGraphs #AI
1
6
428
Enterprise AI is held back less by its models than by missing meaning: the business definitions and relationships an agent needs before it can act with confidence. Straight after the opening keynote on day two, AWS will show how to add that missing layer. Nicole Moldovan and Kevin Phillips will introduce the Context Ontology Accelerator. This open-source AWS project builds ontologies and knowledge graphs from the schemas and documents you already have, then serves them to AI agents. They’ll share measured results from real enterprise deployments: what automation gets right, where a human still has to write the model, how far the approach scales, and why grounding an agent at retrieval time isn’t the same as making it follow the rules. The keynotes are the only part of the programme every delegate attends together, so arrive early for a good seat! The Missing Layer: From Schema to Ontology to Agent 🎤 Nicole Moldovan, Principal Product Manager for Amazon Neptune, AWS 🎤 Kevin Phillips, Senior Specialist Solutions Architect, Amazon Web Services 📅 Thursday 12 November 2026, 10:00 AM - 10:30 AM, Keynotes (Warwick/Salisbury Suite) 📍 Leonardo Royal Hotel London Tower Bridge ⭐ 5 days to go. Seize the opportunity and book your CDL26 pass: sbee.link/87uwjx64y9 sbee.link/-custom-by-source-… #CDL26 #KnowledgeGraphs #Ontology #AIagents #AWS #OpenSource
2
11
631