Triple

T4217131
Position Surface form Disambiguated ID Type / Status
Subject Rocky Balboa E94245 entity
Predicate trainer P41095 FINISHED
Object Mickey Goldmill E62250 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: Mickey Goldmill | Statement: [Rocky Balboa, trainer, Mickey Goldmill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mickey Goldmill
Context triple: [Rocky Balboa, trainer, Mickey Goldmill]
  • A. Mickey Goldmill chosen
    Mickey Goldmill is the gruff, old-school boxing trainer and mentor of Rocky Balboa in the "Rocky" film series.
  • B. Mickey Knox
    Mickey Knox is the violent, media-sensationalized serial killer protagonist from the film "Natural Born Killers."
  • C. Beau Jack
    Beau Jack was a popular American lightweight boxing champion of the 1940s, known for his aggressive style and frequent headline bouts at Madison Square Garden.
  • D. Peter Masterson
    Peter Masterson was an American actor, director, producer, and writer best known for co-writing and co-directing the film adaptation of the musical "The Best Little Whorehouse in Texas."
  • E. Buford "Mad Dog" Tannen
    Buford "Mad Dog" Tannen is the ruthless, hot-tempered outlaw and ancestor of Biff Tannen who serves as the main antagonist in the Old West setting of Back to the Future Part III.
  • 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_69b3451997e08190851db4a9a588837d completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b34beb470481909ceff19195417f19 completed March 12, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a855cfc08190acceced9cb80f41a completed March 14, 2026, 6:26 p.m.
Created at: March 12, 2026, 11:04 p.m.