Extract Events (Timeline)

🤖 AI Drafted (Not reviewed)

Extracts only what a timeline can show: dated events and the dates themselves. Transcribe each page (reusing any existing text layer), name the events, then read each event’s claim and the date the text gives it. Every claim lands as a KnowledgeClaim with time_start / time_end, which is what the KG Timeline plots — no places, no organizations, no per-person loop over pages the timeline will never show. Verbs and objects are copied from the source, so clicking a point on the timeline lands on the words that put it there.

Folder	/Extract
Steps	4
Tags	preset, events, timeline, dates, extract, representation

Steps, in run order

1. Files

Tool: Files — Pass through input files from workflow context

2. Transcribe each file

Tool: Transcribe — Extract text from images (OCR)

Settings this step uses:

Option	Value
language	auto
update_page_content	yes
vision_mode	auto

What this step asks the model:

Transcribe the text visible on this image.

Language: transcribe in the language of the source. Do not translate, and do not assume the document is in English.

Rules:
- Output ONLY the transcription. No headings, no preamble, no commentary,
  no summary, no notes, no explanations, no observations about quality or
  legibility, no descriptions of seals or images, no language about the
  difficulty of the handwriting.
- Preserve original layout, line breaks, and paragraph structure.
- Preserve original spelling and capitalisation, including ALL CAPS
  headers if they appear that way.
- Preserve orthography exactly as written, including all diacritics
  and accent marks (e.g., keep "Chocó" as "Chocó", never "Choco";
  keep "Ramón" as "Ramón", never "Ramon").
- Do not strip accents, tildes, cedillas, or umlauts. If a mark is
  visible, keep it.
- Include every visible text element — headers, body, marginalia, stamps,
  signatures (transcribe the signed name as written), printed labels,
  handwritten annotations.
- For text you cannot confidently read, use explicit uncertainty markers:
  [ilegible] for unreadable text and [uncertain] for plausible-but-low-
  confidence readings. Place the marker inline at the uncertain span.
  Do not guess. Do not fill in.
- Do NOT invent dates, numbers, names, or words that are not legibly
  present. Do not normalise dates ("23/7/1999" stays "23/7/1999", not
  "1999-07-23").
- Do NOT repeat any portion of the transcription. Output each visible
  passage exactly once.
- If the image contains no legible text, output the single token
  [sin texto].

3. Name the events

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

Settings this step uses:

Option	Value
entity_types	events
output_language	auto
provider_name	$small

4. Date the events

Tool: Extract SVO Claims — Extract and persist SVO KnowledgeClaim rows only from existing entities and transcription artifacts

Settings this step uses:

Option	Value
entity_types	events,dates
output_language	auto
provider_name	$small