Triple

T22022285
Position Surface form Disambiguated ID Type / Status
Subject Terminal (2018 film) E543873 entity
Predicate producer P490 FINISHED
Object Margot Robbie 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: Margot Robbie | Statement: [Terminal (2018 film), producer, Margot Robbie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Margot Robbie
Context triple: [Terminal (2018 film), producer, Margot Robbie]
  • A. Margot Robbie chosen
    Margot Robbie is an Australian actress and producer known for her versatile performances in films such as "The Wolf of Wall Street," "I, Tonya," and "Barbie."
  • B. Ruby Rose
    Ruby Rose is an Australian model, DJ, and actress known for her androgynous style and roles in action films and television series such as "Orange Is the New Black."
  • C. Dakota Johnson
    Dakota Johnson is an American actress best known for starring as Anastasia Steele in the film adaptation of the erotic romance novel "Fifty Shades of Grey" and its sequels.
  • D. Elizabeth Debicki
    Elizabeth Debicki is an Australian actress known for her striking performances in films and series such as "The Great Gatsby," "The Night Manager," and "The Crown."
  • E. Ana de Armas
    Ana de Armas is a Cuban-Spanish actress known for her breakout roles in films such as "Blade Runner 2049," "Knives Out," and "Blonde."
  • 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127c8ac6881909a9e96e0873a3ae2 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:23 p.m.