Citation Needed: Provenance for LLM-Built Knowledge Graphs

Official Schedule Context

Official Description

An LLM doesn't copy facts into your knowledge graph. It synthesizes them: entities merge across

sources, and later data invalidates earlier facts. By the time your agent retrieves "patient has a

penicillin allergy," the origin — an EHR record, a lab report, or something typed into a chatbot —

is gone. This talk covers engineering lineage into a lossy, generative pipeline: episode-to-fact

links as structural graph properties, provenance that survives entity resolution, metadata

projection (tag a source once; it follows every derived node and edge), and the query semantics of

filtering facts by ancestry, including mixed-trust parentage. Deletion is the inverse problem: GDPR

erasure propagates back through the same derivation edges. Compliance gets an audit trail; engineers

get agents they can debug instead of black boxes.

Related YouTube Video

Stop Using RAG as Memory — Daniel Chalef, Zep (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Transcript Status

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

People

Notes

Supporting Slides

Slide Evidence