Going Meta S03E03 – Ontologies, LLMs, Property Graphs – Do we really have a “Jaguar Problem”?
Season 03 Episode 3 of Going Meta – a Series on Semantics, Knowledge Graphs and All Things AI
Topic: Ontologies, LLMs, Property Graphs - Do we really have a "Jaguar Problem"?
Jesús Barrasa: https://twitter.com/BarrasaDV
Repository: https://github.com/jbarrasa/goingmeta
Knowledge Graph Book: https://bit.ly/3LaqE6b
Previous Episodes: https://neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/
Niklas Emegard on LinkedIn: https://www.linkedin.com/posts/niklasemegard_graphrag-knowledgegraphs-semanticweb-activity-7390898141820092416-0ojW/
GraphRAG Github Repo: https://github.com/nemegrod/graph_RAG
Going Meta S02E03 - Blueprints: https://www.youtube.com/watch?v=cPzy61odKCg
Chapters
- 00:00Intro
- 04:41What is the “Jaguar Problem”? Context for the 6 claims
- 08:52Inaccuracy #1: “LLMs cannot deal with lexical ambiguity without help”
- 14:28Inaccuracy #2: “Feeding an ontology into the context window guarantees schema alignment”
- 23:02Inaccuracy #3: “Extracted triples require zero post-processing”
- 27:58Inaccuracy #4: “LLMs can run OWL reasoning (formal semantics)”
- 30:58Inaccuracy #5: “LLMs perform better when prompted with RDF/OWL vs natural language”
- 36:49Experimental results comparing NL vs OWL guidance
- 41:02Inaccuracy #6: “This cannot be done with LPG / property graph databases”
- 48:55Takeaways: Ontologies + LLMs + Property Graphs and how they *really* work together
- 57:51Closing Q&A
Related Videos
14:56
070 ESG Supply Chain Knowledge Graph – NODES2022 – Dr. Julian Gruemmer
00:36
Introducing Workspace — The Fastest Way To Build Your Neo4j Database
10:53
