Triple

T5958948
Position Surface form Disambiguated ID Type / Status
Subject Akiva Goldsman E132585 entity
Predicate notableWork P4 FINISHED
Object Cinderella Man E26359 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: Cinderella Man | Statement: [Akiva Goldsman, notableWork, Cinderella Man]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cinderella Man
Context triple: [Akiva Goldsman, notableWork, Cinderella Man]
  • A. Cinderella Man chosen
    Cinderella Man is a 2005 biographical sports drama film about Depression-era boxer James J. Braddock, starring Russell Crowe and directed by Ron Howard.
  • B. National Velvet
    National Velvet is a classic 1944 family sports drama film about a young girl and her horse competing in the Grand National steeplechase.
  • C. Seabiscuit
    Seabiscuit is a 2003 sports drama film about an undersized Depression-era racehorse and his unlikely team, adapted from Laura Hillenbrand’s nonfiction book.
  • D. Scent of a Woman
    Scent of a Woman is a 1992 drama film in which Al Pacino delivers an Oscar-winning performance as a blind, irascible former Army officer.
  • E. Hud
    Hud is a prophet in Islamic tradition, known for being sent to guide the ancient people of ʿĀd away from idolatry and toward the worship of one God.
  • 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_69c0086c2364819091e9fe2f58fa2517 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c039c48d0c81908e794c52fddf2ca2 completed March 22, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3e3736c8190b445156f0c1bdf1f completed March 23, 2026, 6:55 a.m.
Created at: March 22, 2026, 4:02 p.m.