Triple

T23002237
Position Surface form Disambiguated ID Type / Status
Subject Polar (2019 film) E572664 entity
Predicate starring P1507 FINISHED
Object Anthony Grant 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: Anthony Grant | Statement: [Polar (2019 film), starring, Anthony Grant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony Grant
Context triple: [Polar (2019 film), starring, Anthony Grant]
  • A. Anthony Grant chosen
    Anthony Grant is an actor known for his role in the action-comedy film "Polar."
  • B. Frank Haith
    Frank Haith is an American college basketball coach best known for leading programs such as the Miami Hurricanes, Missouri Tigers, and Tulsa Golden Hurricane men's teams.
  • C. Gregg Marshall
    Gregg Marshall is an American college basketball coach best known for his long, successful tenure at Wichita State University, where he built the Shockers into a national contender.
  • D. Dan McGuire
    Dan McGuire is best known as the husband of American artist Margaret Keane, whose distinctive "big eyes" paintings gained widespread fame.
  • E. Mark Turgeon
    Mark Turgeon is an American college basketball coach best known for leading the University of Maryland men's basketball program through much of the 2010s and early 2020s.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18353d05481909abacb48a14ef21e completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:50 p.m.