Triple

T22980889
Position Surface form Disambiguated ID Type / Status
Subject George Forrest E571459 entity
Predicate notableWork P4 FINISHED
Object Timbuktu! NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Timbuktu! | Statement: [George Forrest, notableWork, Timbuktu!]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Timbuktu!
Context triple: [George Forrest, notableWork, Timbuktu!]
  • A. Timbuktu! chosen
    Timbuktu! is a 1978 Broadway musical adaptation of Kismet, set in the African kingdom of Mali and originally starring Eartha Kitt.
  • B. Timbuktu
    Timbuktu is an ancient city in Mali famed as a historic center of trans-Saharan trade and Islamic scholarship.
  • C. Timbuktu: City of 333 Saints
    Timbuktu: City of 333 Saints is a historic Malian desert city famed as a medieval center of Islamic scholarship and trans-Saharan trade, renowned for its ancient mosques and manuscript libraries.
  • D. Western Songhay of Timbuktu
    Western Songhay of Timbuktu is a variety of the Songhay language spoken around Timbuktu in Mali, known locally as Koyra Chiini.
  • E. Téboursouk
    Téboursouk is a town in northern Tunisia known as a gateway to the nearby ancient Roman ruins of Dougga.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e245b3c50481908bb3741ec9f40862 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1829589548190863619aebcae026c completed April 29, 2026, 4:01 a.m.
Created at: April 17, 2026, 3:49 p.m.