Triple

T20877869
Position Surface form Disambiguated ID Type / Status
Subject James "Whitey" Bulger E514067 entity
Predicate nickname P55 FINISHED
Object Whitey 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: Whitey | Statement: [James "Whitey" Bulger, nickname, Whitey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Whitey
Context triple: [James "Whitey" Bulger, nickname, Whitey]
  • A. Whitey
    Whitey is the nickname of Hall of Fame New York Yankees pitcher Whitey Ford, one of Major League Baseball’s most successful left-handed pitchers.
  • B. Whitey
    Whitey is the nickname of Hall of Fame Major League Baseball manager Whitey Herzog, renowned for his success with the St. Louis Cardinals in the 1980s.
  • C. Whitey
    Whitey was the nickname of Richie Ashburn, a Hall of Fame center fielder best known for his years with the Philadelphia Phillies and later work as a beloved broadcaster.
  • D. Whitey chosen
    "Whitey" is a true-crime book by journalist Dick Lehr that chronicles the life, crimes, and capture of Boston mob boss James "Whitey" Bulger.
  • E. Whitey Marsh
    Whitey Marsh is the tough, streetwise orphan who becomes the central reformed youth in the classic 1938 film "Boys Town."
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c6775f108190a79cd5e8c31cecf6 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:45 p.m.