Triple

T20807910
Position Surface form Disambiguated ID Type / Status
Subject Stablemates E512212 entity
Predicate director P255 FINISHED
Object Sam Wood 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: Sam Wood | Statement: [Stablemates, director, Sam Wood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sam Wood
Context triple: [Stablemates, director, Sam Wood]
  • A. Sam Wood
    Sam Wood is a small-town police officer who becomes entangled in a racially charged murder investigation in John Ball’s novel "In the Heat of the Night."
  • B. Sam Wood chosen
    Sam Wood was an American film director best known for his work during Hollywood’s Golden Age, including classics such as "A Night at the Opera," "Goodbye, Mr. Chips," and "The Pride of the Yankees."
  • C. Roger Spottiswoode
    Roger Spottiswoode is a British-Canadian film director and editor known for directing a range of Hollywood features, including the James Bond film "Tomorrow Never Dies."
  • D. Lee M. Russell
    Lee M. Russell was an American Democratic politician who served as governor of Mississippi in the early 20th century.
  • E. Christopher Landon
    Christopher Landon is an American film director, screenwriter, and producer best known for his work on the "Paranormal Activity" series and the "Happy Death Day" films.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2d0a2a081908fb0e3d890e87aaf completed April 21, 2026, 12:20 a.m.
Created at: April 16, 2026, 12:40 p.m.