surface↓extraction↓timeline
Extractionscalar · returns json

TIMELINE

Extract chronologically ordered events from text

Per-row — runs once for each row.

extractionllmtext

Syntax

TIMELINE({{ text }})
TIMELINE({{ text }}, '{{ reference_date }}')
{{ text }} TIMELINE

Arguments

nametypedescription
textVARCHAR—
reference_date(optional)VARCHARReference date for resolving relative times (e.g., 'yesterday')

About

Extract temporal events from text and order them chronologically. Turns unstructured narratives, emails, logs, or documents into ordered sequences of events with timestamps (absolute or relative). Perfect for: - Reconstructing sequences of events from emails/documents - Log analysis and incident timelines - Project history extraction - Legal discovery (what happened when?) - Meeting notes → action item timelines

Examples

Extracts ordered events with relative dates

SELECT
  timeline (
    'We met on Monday to discuss the proposal. By Wednesday, the contract was signed. The project launched the following week.'
  )

Extracts precise timestamps

SELECT
  timeline (
    'The server crashed at 3:15 PM. We identified the issue at 3:45 PM and deployed a fix at 4:30 PM.'
  )

Nearby rabbit holes

same domain
scalar

CRAWL_BATCH

Crawl a website and extract structured data from each page (via Firecrawl)

extractionexternal-apiurl
scalar

EXTRACT

Extract specific information from unstructured text (zero-shot NER)

extractionnlispecialist-zootext
scalar

EXTRACT_LLM

LLM-backed extraction (escape hatch for EXTRACTS)

extractionllmllm-escape-hatchtext
scalar

EXTRACT_STRUCTURED

Extract structured fields from text per a user-supplied schema

extractionllmtext
aggregate

MERGE_TIMELINES

Merge multiple timelines into unified chronological sequence

extractionllmjson
scalar

PARSE

Extract information from text using natural-language instructions

extractionllmtext
Climb back to The Looking Glass