https://drive.google.com/file/d/1FrPnqXsSJQhTxzRb-bsnVHP99nC82sbF/view?usp=share_link

At Netflix, dozens of data systems coexist: GraphQL APIs, Avro/Flink pipelines, Iceberg tables, OpenSearch indexes, etc. Each system defines its own schemas, its own understanding of what ""Movie"" or ""Talent"...

https://drive.google.com/file/d/1ZB1dp5MoGoSHLLLx06WWLTj5sq9ZVKVI/view?usp=share_link

This presentation details the evolution of our graph-enabled advanced risk reporting system, highlighting the transformative role of ontology in enabling critical data views and broadening audience engagement a...

https://drive.google.com/file/d/1fTSRdxgfz-ykrRa3eO9Iw48GHs1rO3p0/view?usp=share_link
AI agents don't search. They need to understand. And understanding requires a world model: a living representation of how your business actually works.

The knowledge graph is the right foundation. But three har...

Fragmented data prevents accurate Customer 360. Entity resolution connects siloed records, improving knowledge graphs and AI-driven insights. Though as AI apps scale, how do we ensure trust in what gets generated? Join this fireside discussion with the technical visionary team of a UK public sect...

During a recent engagement, Factor led a client effort to migrate from a traditional RDBMS-based taxonomy management system to a graph-based environment.

The client's semantic ecosystem was complex, comprising dozens of taxonomes managed in two separate toolsets (a taxonomy management tool and a...

A chatbot by CSI-Piemonte serves millions of citizens consulting public recruitment competitions and exam schedules. Competitions publish official notices as PDFs defining exam sessions segmented by region, surname ranges, and candidate codes. These notices are continuously amended by corrections...

Many organisations are investing in AI to automate complex workflows, but often encounter the same challenges: systems that are difficult to trust, hard to explain, and risky to operate at scale. In this joint talk, Marketer.com and Oxford Semantic Technologies show how a knowledge graph–driven ...

Haven't you heard? ""You don't have a knowledge problem. You have a context problem.""

This framing has resonated with business leaders in a way that ""knowledge graph"" or ""semantic layer"" often hasn't — and if you're in this room, you already know why. Context is the thing AI actually needs ...

https://drive.google.com/file/d/12tENn562wJeLwH0ppQOQ1IIH-GuJSrXL/view?usp=share_link

In a globalized world, commerce is increasingly complex with billions of daily transaction across millions of businesses. The unique patterns which exists in the business landscape supports numerous use cases a...

https://drive.google.com/file/d/1BZnMLbRIH0ZU-8ulqUZ9oCeqI1ZjGE1y/view?usp=share_link

Joint proposal with Adrian Gschwend and Pierre-Antoine Champin

RDF 1.2 is the culmination of years of work on improving the usability of reification in RDF. As the W3C RDF and SPARQL Working Group is nearing t...

AI, graph analytics, and enterprise database features simplify building intelligent, connected applications. Hear from Industrial Scientific, a world leader in gas detection for worker safety programs, who was facing data integrity challenges because of data inconsistencies across multiple system...

Most multimodal RAG stacks have a “split-brain” design: embeddings in a vector DB, relationships in a graph DB, and images/video/audio in blob storage. For an agent, that becomes a slow three-hop loop—similarity search, graph traversal, then a network fetch to load the actual frames for a VLM. Th...

https://drive.google.com/file/d/16JcyI8agX69uv4bGb_oV1LCuR-tzSmhZ/view?usp=share_link

Behind every public market lies an invisible network of investors, investees, and shared board seats — relationships. This talk shares how we combined Amazon Neptune's graph database capabilities with Linkuriou...

https://drive.google.com/file/d/1ppJ1SP6ISzKVa_Vu5K1BNVPfC4yQZxYZ/view?usp=share_link

Accounting is a last remaining hurdle enterprises face on their journeys to become fully data-centric. Instead of relying on centuries-old artifacts such as journals, ledgers, debits and credits, Data-Centric A...

https://drive.google.com/file/d/1dXvbNAZw9mdxcL74IRM705kESz4f-xpL/view?usp=share_link

We present an extensible framework specifically designed for the Competency Question-to-Ontology generation, which evaluates a growing set of models from major providers on their ability to generate formal onto...

Hedge funds and trading firms face an insurmountable challenge: synthesizing insights from market data, SEC filings, earnings transcripts, expert interviews, and research reports at scale. This presentation demonstrates a production knowledge graph system that automatically bridges structured fin...

"https://drive.google.com/file/d/1oF6pLrXoVYKh_GRpyC-E4hmFRnzdOF9a/view?usp=share_link

Qualification processes in industrial settings require accurate, equipment-specific inspection criteria from technical documentation to ensure deliverable quality and minimize post-launch downtime and claims. ...

Traditional Enterprise Knowledge Graphs rely on upfront Entity Resolution (ERRP) that strips away nuance. These heavy build-time commitments create brittle pipelines and discard the contextual signals necessary for handling unstructured data like SEC filings or risk disclosures.

Methodology JIT-...

- Can an open source GRC agentic ecosystem powered by a standards-based GRC knowledge graph audit-by-prompt to identify control gaps and risks for ever changing assets, threats, defense, and regulatory landscapes?

Until recently that was not possible but now GRC AI agents can perform such work a...

https://drive.google.com/file/d/1U69x-1YmM3H_V7EW9i-_uX7HHSSHZYs7/view?usp=share_link
This joint talk, by two researchers who have coined well known ‘slogans’ in the knowledge graph community, Jim Hendler, credited with “a little semantics goes a long way” and Deborah McGuinness, known for sayin...

https://drive.google.com/file/d/1047w3_Vfg6FGK8HdLFp95NgjucDsxlzO/view?usp=share_link

The Spatial Web, as defined by the IEEE P2874 standard, extends the World Wide Web and traditional knowledge graphs beyond static facts to include entities, spaces, behaviors, and governance spanning the physic...

"https://drive.google.com/file/d/1hOTo6TMxTcq0bs8YjfIAEHnzA7fN8yyn/view?usp=share_link

Few industries have more pressure to get data semantics right than financial services. Yet approaches vary wildly, from mature knowledge and context graph implementations to firms still debating whether the in...

https://drive.google.com/file/d/1U8MsBuIhegD36f3s6OuxCAdAhBEY_9Dr/view?usp=share_link

Database workload modernization fails when dependency graphs lack the semantic context to capture the ""why"" and ""how"" behind components and their connections. We present a framework based on LangGraph, tran...