Triple

T2007758
Position Surface form Disambiguated ID Type / Status
Subject Royal Wedding E43623 entity
Predicate director P255 FINISHED
Object Stanley Donen E45045 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: Stanley Donen | Statement: [Royal Wedding, director, Stanley Donen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stanley Donen
Context triple: [Royal Wedding, director, Stanley Donen]
  • A. Stanley Donen chosen
    Stanley Donen was an American film director and choreographer best known for co-directing classic Hollywood musicals such as "Singin' in the Rain" and "On the Town."
  • B. Vincente Minnelli
    Vincente Minnelli was an American film director best known for his visually distinctive and influential Hollywood musicals, including classics like "An American in Paris" and "Gigi."
  • C. Blake Edwards
    Blake Edwards was an American filmmaker best known for his stylish comedies and classics like the Pink Panther series and Breakfast at Tiffany’s.
  • D. Michael Curtiz
    Michael Curtiz was a Hungarian-American film director best known for helming classic Hollywood films such as "Casablanca."
  • E. Robert Aldrich
    Robert Aldrich was an American film director and producer known for his gritty, hard-edged movies such as "Kiss Me Deadly," "What Ever Happened to Baby Jane?" and "The Dirty Dozen."
  • 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_69a88716e9f08190946313fdc949e3cf completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb89aca908190b8b659af65afdf6f completed March 7, 2026, 5:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae3048a15881909db68dfe7dc7bcf0 completed March 9, 2026, 2:28 a.m.
Created at: March 4, 2026, 7:37 p.m.