2 · Extract Entities

🤖 AI Drafted (Not reviewed)

Step 2 of the discrete import-artifacts pipeline. Reuse the transcription artifacts from step 1 to extract and persist entity rows only. Safe to re-run: entity upserts reuse existing rows and accumulate per-page provenance without duplicates.

Folder	/Catalogue
Steps	2
Tags	preset, catalogue, stage, entities, reviewable

Steps, in run order

1. Files

Tool: Files — Pass through input files from workflow context

2. Extract entities

Tool: Extract Entities — Extract and persist entity rows only from existing transcription artifacts

Settings this step uses:

Option	Value
output_language	auto
provider_name	$small