Triple

T10190901
Position Surface form Disambiguated ID Type / Status
Subject Joan Cohl E238028 entity
Predicate partnerOf P1136 FINISHED
Object Dusty Cohl E46651 NE FINISHED

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: Dusty Cohl | Statement: [Joan Cohl, partnerOf, Dusty Cohl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dusty Cohl
Context triple: [Joan Cohl, partnerOf, Dusty Cohl]
  • A. Dusty Cohl chosen
    Dusty Cohl was a Canadian film producer and cultural promoter best known for co-founding the Toronto International Film Festival and helping elevate Toronto’s global film profile.
  • B. Dixie Walker
    Dixie Walker was an American Major League Baseball right fielder, best known as a star player for the Brooklyn Dodgers in the 1940s and a two-time National League batting champion.
  • C. Tonya Pinkins
    Tonya Pinkins is a Tony Award–winning American actress and singer known for her powerful performances on Broadway, in film, and on television.
  • D. Kathy Summerall
    Kathy Summerall is known as the wife of legendary American sportscaster and former NFL player Pat Summerall.
  • E. Martine Bancroft
    Martine Bancroft is a Marvel Comics character closely associated with the antihero Morbius, often depicted as his fiancée and a key emotional anchor in his storyline.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84de1b208190bf17bb305b002605 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cded7eb1148190a2d175163685e233 completed April 2, 2026, 4:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69d32ae3fe40819093080f9bf15a9608 completed April 6, 2026, 3:39 a.m.
Created at: March 30, 2026, 9:13 p.m.