Triple

T3197132
Position Surface form Disambiguated ID Type / Status
Subject Saboteur E66960 entity
Predicate screenwriter P2831 FINISHED
Object Joan Harrison E117742 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: Joan Harrison | Statement: [Saboteur, screenwriter, Joan Harrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan Harrison
Context triple: [Saboteur, screenwriter, Joan Harrison]
  • A. Joan Harrison chosen
    Joan Harrison was a prominent British-born screenwriter and producer best known for her collaborations with Alfred Hitchcock and her influential work in classic Hollywood cinema.
  • B. Alma Reville
    Alma Reville was a British screenwriter, editor, and assistant director best known for her long creative collaboration with and marriage to filmmaker Alfred Hitchcock.
  • C. Louise Dahl-Wolfe
    Louise Dahl-Wolfe was a pioneering American fashion photographer renowned for her innovative use of natural light and location shooting, which helped redefine modern fashion imagery in the mid-20th century.
  • D. Wanda Ventham
    Wanda Ventham is an English actress known for her extensive work in British television and film, and as the mother of actor Benedict Cumberbatch.
  • E. Edith Head
    Edith Head was a legendary American costume designer in Hollywood, renowned for her work on classic films and for holding the record for the most Academy Awards won by a woman.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7192994819084817307065a25e2 completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24bb7cd488190ae95c140d9cda296 completed March 12, 2026, 5:14 a.m.
Created at: March 8, 2026, 3:07 p.m.