Triple

T20469127
Position Surface form Disambiguated ID Type / Status
Subject Peter Hyams E502136 entity
Predicate relative P37 FINISHED
Object John Hyams 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: John Hyams | Statement: [Peter Hyams, relative, John Hyams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Hyams
Context triple: [Peter Hyams, relative, John Hyams]
  • A. John Hyams chosen
    John Hyams is an American film and television director, producer, and screenwriter known for his work in action and horror, including the series "Black Summer" and entries in the "Universal Soldier" franchise.
  • B. Tom Hiel
    Tom Hiel is an American film and television composer known for scoring a variety of genre projects, including cult and horror films.
  • C. Peter Hyams
    Peter Hyams is an American filmmaker known for directing and often writing and shooting genre films such as science fiction thrillers and action movies.
  • D. Abby Mann
    Abby Mann was an American screenwriter and producer best known for his socially conscious dramas, including the Academy Award–winning screenplay for "Judgment at Nuremberg."
  • E. Tim Van Patten
    Tim Van Patten is an American television director, producer, and former actor known for his work on acclaimed series such as The Sopranos, Boardwalk Empire, and Game of Thrones.
  • 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6995f753081909bbe03f7c251d9c1 completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:33 a.m.