Show HN: We had AI write a wiki from 45k Enron emails, every fact cited

Category: ai-ml

Tags: ai, knowledge-graph, citations, enron, temporal-facts

Score: 5.7/10 (Innovation: 7, Technical: 6, Documentation: 6, Utility: 4)

This project uses an AI pipeline to generate a wiki from 45,000 Enron emails, producing 214 entity pages with 49,401 facts, each citing a specific email and expiring when facts become outdated. It demonstrates a novel approach to grounded, citation-based knowledge extraction and temporal fact management, though it remains a prototype with limited general applicability.

Target audience: AI researchers, knowledge management engineers, and developers interested in fact extraction and citation-grounded generation

Repository: https://www.thisandthat.chat/enron/

View on Hacker News