Triple

T15465130
Position Surface form Disambiguated ID Type / Status
Subject Bill Donovan E372012 entity
Predicate name P16 FINISHED
Object Bill Donovan E372012 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: Bill Donovan | Statement: [Bill Donovan, name, Bill Donovan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Donovan
Context triple: [Bill Donovan, name, Bill Donovan]
  • A. Bill Donovan chosen
    Bill Donovan was an early 20th-century Major League Baseball pitcher and manager, best known as a star hurler for the Detroit Tigers.
  • B. Jeff Calhoun
    Jeff Calhoun is an American theater director and choreographer known for his work on numerous Broadway and touring productions, including the stage adaptation of Disney’s Newsies.
  • C. Bill Fitch
    Bill Fitch was an American basketball coach best known for leading the Boston Celtics to the 1981 NBA championship and for his reputation as a demanding, turnaround specialist.
  • D. Jim Cavanaugh
    Jim Cavanaugh is an American businessman and aviation enthusiast best known as the founder of the Cavanaugh Flight Museum, which preserves and displays historic aircraft.
  • E. Len Kaminski
    Len Kaminski is an American comic book writer best known for his work at Marvel Comics in the 1990s, particularly on Iron Man-related titles and other superhero series.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f680cec8190836a5ec841dee224 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d4448c08190ac640642cc8fc41f completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 3:33 a.m.