Triple

T9236202
Position Surface form Disambiguated ID Type / Status
Subject Roma (2018 film) E221942 entity
Predicate portrayedBy P1507 FINISHED
Object Yalitza Aparicio E373950 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: Yalitza Aparicio | Statement: [Roma (2018 film), portrayedBy, Yalitza Aparicio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yalitza Aparicio
Context triple: [Roma (2018 film), portrayedBy, Yalitza Aparicio]
  • A. Yalitza Aparicio chosen
    Yalitza Aparicio is a Mexican actress and former preschool teacher who gained international acclaim and an Academy Award nomination for her debut performance in Alfonso Cuarón’s film "Roma."
  • B. Sofía García
    Sofía García is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the García surname.
  • C. Angélica Fuentes
    Angélica Fuentes is a Mexican businesswoman and philanthropist known for her leadership in the energy and nutrition sectors and for being one of Latin America’s most influential female executives.
  • D. Lorena Bernal
    Lorena Bernal is an Argentine-born Spanish actress, model, and former Miss Spain who has also worked as a television presenter.
  • E. Adriana Barraza
    Adriana Barraza is a Mexican actress and director acclaimed for her powerful performances in films such as "Babel," for which she received an Academy Award nomination.
  • 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_69ca83ed628c8190bc02d641e57f097f completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccf09d42488190b8ccb9c4b62fdda8 completed April 1, 2026, 10:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077cc774c8190bdbdd4071c11f096 completed April 4, 2026, 2:30 a.m.
Created at: March 30, 2026, 7:29 p.m.