Triple

T16509516
Position Surface form Disambiguated ID Type / Status
Subject Kent Alterman E401020 entity
Predicate directed P7373 FINISHED
Object "Semi-Pro" E76736 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: "Semi-Pro" | Statement: [Kent Alterman, directed, "Semi-Pro"]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: "Semi-Pro"
Context triple: [Kent Alterman, directed, "Semi-Pro"]
  • A. Semi-Pro chosen
    Semi-Pro is a 2008 sports comedy film starring Will Ferrell as the owner-coach-player of a struggling 1970s ABA basketball team.
  • B. Knockaround Guys
    Knockaround Guys is a 2001 crime thriller film about the sons of Brooklyn mobsters trying to prove themselves, produced by Lawrence Bender.
  • C. The Rookie
    The Rookie is a 2002 sports drama film based on the true story of high school teacher and former pitcher Jim Morris, who makes an unexpected late-in-life debut in Major League Baseball.
  • D. The Rookie
    The Rookie is a 1959 American comedy film starring and co-written by comedian Frank Stanley.
  • E. The Sixth Man
    The Sixth Man is a 1997 sports comedy‑fantasy film about a college basketball player who is helped by the ghost of his deceased brother and teammate.
  • 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e54f7508190804bbae4c9bc8fe3 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a005833ef9c8190a2ff440942b83dc8 completed May 10, 2026, 10:04 a.m.
Created at: April 10, 2026, 5:14 a.m.