NER per-page (local)
🤖 AI Drafted (Not reviewed)
Local NER extraction over a folder of text files (.md / .txt). No transcription step (text already has page_content); no folder cleanup; no aggregate-combine output. Each file gets its own per-doc people / places / organizations / dates / events / keywords artifacts, and factual KG claims persist inline during extraction. Uses the $small alias — point it at Apple Intelligence in Settings → AI Defaults to keep everything on-device. Designed for field notes, journals, and any plain-text corpus where you want entity extraction without burning cloud tokens.
| Folder | /Catalogue |
| Steps | 3 |
| Tags | preset, ner, local, text, field-notes |
Steps, in run order
1. Files (text)
Tool: Files — Pass through input files from workflow context
2. Collect per-file text
Tool: Aggregate — Combine upstream fan-out results into a single payload.
Settings this step uses:
| Option | Value |
|---|---|
mode |
concat |
separator |
— |
3. Extract entities (per-page)
Tool: Extract All Entities — Single-pass extraction of people, places, organisations, dates, events, and keywords. One LLM call per page returns all six types as JSON — 6× fewer calls than the per-type extractors, same downstream shape (KG claims + per-page artifacts).
Settings this step uses:
| Option | Value |
|---|---|
output_language |
auto |
persist_kg |
yes |
provider_name |
$small |
What this step asks the model:
You are an expert archivist extracting structured entities from a document. Extract evidence, not ontology labels. Do NOT emit generic claims like 'Pedro is a person', 'Colombia is a location', or 'cash is a concept'. Entity type is metadata only. For each useful entity or index term, extract specific SVO facts grounded in nearby text, with source_text as a short exact quote from the page, preserving any [ilegible] / [uncertain] markers exactly as written. Cover repeated useful facts for the same entity when the text supports them. Only include facts the text supports — do not speculate or invent. Keywords are book-index terms for finding this page later: include relevant concepts, subjects, and names only when they help locate the passage; do not pad to a quota. Write prose fields in English. Use verbs from the page context for ordinary claims. Reserve reporting verbs (said, stated, declared, asserted, claimed, testified, petitioned, reported, argued, wrote, denied, requested) for direct quotations or explicitly attributed statements only.
Section-specific guidance:
- people: named people or named groups only. Extract specific facts about what they did, used, worked, produced, relied on, valued, or experienced. Do not use reporting verbs unless the text directly quotes or attributes speech.
- places: named places or geographic regions with a specific relationship stated by the text. This includes geographic and land-use CATEGORIES, not just proper names: 'agricultural zones', 'mining districts', 'territories' all belong here. If a term denotes a location or land area — even a generic one — it is a place, NOT a keyword/concept.
- organizations: named organizations only.
- dates: dates stated in the text, with the event or condition attached to that date.
- events: occurrences explicitly stated by the text. This includes unnamed/generic occurrences: 'accident', 'flood', 'death', 'fire' are events, NOT keywords/concepts. If a term denotes something that happened, it is an event.
- quotes: direct quotations only, where the source gives quoted words or an explicit speaker/writer attribution.
- keywords: the 5-8 MOST SALIENT, distinctive keywords for ABSTRACT ideas only — themes, subjects, time periods, ideologies. Do NOT put places, events, people, or organizations here. If a term names a location (even 'agricultural zones') it belongs in places; if it names an occurrence (like 'accident' or 'flood') it belongs in events. Keywords are concepts, not concrete entities.