BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260429T054959Z
DESCRIPTION:Click for Latest Location Information: http://dgiq-edw2026.data
 versity.net/sessionPop.cfm?confid=165&proposalid=16651\nAfter 18 years of d
 ata governance consulting, I kept running into the same problem: the rules 
 that define how data should look — standards, regulations, contracts,
  SOPs — live in unstructured documents, while the data we govern live
 s in structured systems. We governed the downstream but left the upstream l
 ocked in Docs.\n\nWhen LLMs became capable enough, I asked a simple questio
 n: What if we could automatically extract governed, structured knowledge di
 rectly from those documents — not just search them, but truly underst
 and them with domain context? \n\nOver the past two years, I designed and t
 ested an ontology-driven extraction approach across multiple industries &md
 ash; investment contracts, government policy reports, industrial quality in
 spection, and enterprise semantic enrichment. The core method: domain exper
 ts define "what to look for" through reusable ontology templates,
  and LLMs execute a multi-phase pipeline — from entity recognition th
 rough relationship discovery to risk identification.
DTSTART:20260506T150000
SUMMARY:From Docs to Governed Knowledge: Using AI to Bridge Structured and 
 Unstructured Data
DTEND:20260506T154459
LOCATION: See Description
END:VEVENT
END:VCALENDAR