Triple

T3376737
Position Surface form Disambiguated ID Type / Status
Subject Iron Man 3 E71082 entity
Predicate castMember P1668 FINISHED
Object William Sadler E194689 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: William Sadler | Statement: [Iron Man 3, castMember, William Sadler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Sadler
Context triple: [Iron Man 3, castMember, William Sadler]
  • A. William Sadler chosen
    William Sadler is an American character actor known for his versatile roles in film and television, including memorable performances in dramas, comedies, and genre films.
  • B. Justin Haythe
    Justin Haythe is a British-American screenwriter and novelist known for adapting literary works into acclaimed films such as "Revolutionary Road" and "A Cure for Wellness."
  • C. Clifton James
    Clifton James was an American character actor best known for his comic portrayals of Southern lawmen in films such as the James Bond movies Live and Let Die and The Man with the Golden Gun.
  • D. Robert Slaughter
    Robert Slaughter was the husband of longtime U.S. Representative Louise Slaughter.
  • E. Harry Joe Brown
    Harry Joe Brown was an American film producer best known for his work on classic Westerns and collaborations with stars like Randolph Scott.
  • 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_69ad85a7f80c8190a05e43013f298942 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb2e776508190bc123fb17b36f062 completed March 8, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b334490bf08190aa119e72d12f5e4b completed March 12, 2026, 9:46 p.m.
Created at: March 8, 2026, 3:13 p.m.