Triple

T8956754
Position Surface form Disambiguated ID Type / Status
Subject Red River E213489 entity
Predicate director P255 FINISHED
Object Howard Hawks E17746 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: Howard Hawks | Statement: [Red River, director, Howard Hawks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Hawks
Context triple: [Red River, director, Howard Hawks]
  • A. Howard Hawks chosen
    Howard Hawks was a versatile and influential American filmmaker of the Hollywood Golden Age, renowned for directing classic films across genres including screwball comedies, film noir, westerns, and adventure dramas.
  • B. Raoul Walsh
    Raoul Walsh was a prolific American film director and actor known for his influential work in early Hollywood cinema, particularly in action, adventure, and crime films.
  • C. Ray Stark
    Ray Stark was a prominent American film producer known for backing major Hollywood hits from the 1960s onward, often collaborating with top stars and directors.
  • D. Michael Curtiz
    Michael Curtiz was a Hungarian-American film director best known for helming classic Hollywood films such as "Casablanca."
  • E. John Sturges
    John Sturges was an American film director best known for his classic action and Western films, including "The Great Escape" and "Bad Day at Black Rock."
  • 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_69ca8399ad2081909f8fa41d4314c215 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6728965881908e9f14aaee0c5a18 completed April 1, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc216ff2c819098056dff0de9479f completed April 3, 2026, 1:35 p.m.
Created at: March 30, 2026, 7 p.m.