Ontologies, LLMs, Property Graphs – Do we really have a “Jaguar Problem”?

  • Season 3 · Episode 3 of 11
  • Length: 1 hr 0 min
Play video on YouTube: Ontologies, LLMs, Property Graphs – Do we really have a “Jaguar Problem”?
Neo4j on YouTube
Watch on YouTube (opens in a new tab)
  1. Play from Intro
  2. Play from What is the “Jaguar Problem”? Context for the 6 claims
  3. Play from Inaccuracy #1: “LLMs cannot deal with lexical ambiguity without help”
  4. Play from Inaccuracy #2: “Feeding an ontology into the context window guarantees schema alignment”
  5. Play from Inaccuracy #3: “Extracted triples require zero post-processing”
  6. Play from Inaccuracy #4: “LLMs can run OWL reasoning (formal semantics)”
  7. Play from Inaccuracy #5: “LLMs perform better when prompted with RDF/OWL vs natural language”
  8. Play from Experimental results comparing NL vs OWL guidance
  9. Play from Inaccuracy #6: “This cannot be done with LPG / property graph databases”
  10. Play from Takeaways: Ontologies + LLMs + Property Graphs and how they *really* work together
  11. Play from Closing Q&A

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"?

Resources mentioned

GenAI & GraphRAGKnowledge graphs

Related videos

Browse all videos