surface↓extraction↓merge_timelines
Extractionaggregate · returns json

MERGE_TIMELINES

Merge multiple timelines into unified chronological sequence

Per-group — reads the whole group in one call.

extractionllmjson

Syntax

MERGE_TIMELINES({{ timelines }})

Arguments

nametypedescription
timelinesJSONArray of timeline arrays to merge

About

Merge multiple timelines into a unified chronological sequence. Takes timelines extracted from multiple documents (emails, logs, reports) and synthesizes them into a single coherent narrative, resolving conflicts and filling gaps. Perfect for: - Reconstructing events from email threads - Merging incident reports from multiple sources - Building case timelines from scattered documents - Cross-referencing witness statements

Examples

Merges two simple timelines

SELECT
  merge_timelines (
    '[
  [{"timestamp": "2001-05-14", "event": "Meeting held", "type": "communication", "sequence": 1}],
  [{"timestamp": "2001-05-15", "event": "Contract signed", "type": "decision", "sequence": 1}]
]'
  )

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
scalar

PARSE

Extract information from text using natural-language instructions

extractionllmtext
scalar

PARSE

Parse, validate, or transform patterned strings using plain-English instructions

extractionllmtextpipeline-composable
Climb back to The Looking Glass