Triple

T18258125
Position Surface form Disambiguated ID Type / Status
Subject David Anspaugh E437268 entity
Predicate directed P7373 FINISHED
Object Hoosiers 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: Hoosiers | Statement: [David Anspaugh, directed, Hoosiers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hoosiers
Context triple: [David Anspaugh, directed, Hoosiers]
  • A. Hoosiers chosen
    Hoosiers is a 1986 sports drama film about a small-town Indiana high school basketball team’s underdog run to the state championship, widely regarded as one of the greatest sports movies ever made.
  • B. Hoosiers
    Hoosiers is the nickname commonly used for Indiana University athletic teams and their supporters, especially associated with the state of Indiana.
  • C. 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.
  • D. Hud
    Hud is a 1963 American Western drama film, directed by Martin Ritt and starring Paul Newman, acclaimed for its stark portrayal of moral conflict and its Oscar-winning performances.
  • E. The Kid from Kokomo
    The Kid from Kokomo is a 1939 American comedy film featuring actress Rita Johnson in a prominent role.
  • 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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4fd8879e88190893f8da7c3529496 completed April 19, 2026, 4:06 p.m.
Created at: April 10, 2026, 10:34 a.m.