Storing a simple source ID on a fact works well in structured data warehouses or data lakes where a pipeline outputs one value that is copied or mutated deterministically and sources are known and easily marked, but this breaks with context pipelines run by LLMs.
causalpending
Speaker
Daniel UrsellEvidence Quote
“This can work well in structured data warehouses or data lakes. A pipeline outputs one value copied or mutated deterministically, and the sources are known and easily marked. But with context pipelines run by LLMs, this breaks in several ways.”
Source
Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI— AI EngineerCreated: 8/12/2026, 5:58:29 PM
Your notes
Loading notes...