Triple

T20398153
Position Surface form Disambiguated ID Type / Status
Subject A Ticket to Tomahawk E500261 entity
Predicate screenwriter P2831 FINISHED
Object Mary Loos 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: Mary Loos | Statement: [A Ticket to Tomahawk, screenwriter, Mary Loos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Loos
Context triple: [A Ticket to Tomahawk, screenwriter, Mary Loos]
  • A. Mary Loos chosen
    Mary Loos was an American screenwriter and author known for her work in mid-20th-century Hollywood film and television.
  • B. Mary Looram
    Mary Looram is an actress known for her role in the film "Like Father."
  • C. Eileen Morrow
    Eileen Morrow is a person notable enough to be recognized as a significant bearer of the surname Morrow.
  • D. Joan Lorring
    Joan Lorring was a Hong Kong–born American actress best known for her acclaimed film and television roles in the 1940s and 1950s, including an Academy Award–nominated performance in "The Corn Is Green."
  • E. Kat Morris
    Kat Morris is an American animator, writer, and storyboard artist best known for her creative leadership on the animated series Steven Universe and its related projects.
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6798c2b28819092fab93f01218cde completed April 20, 2026, 7:07 p.m.
Created at: April 16, 2026, 11:29 a.m.