Triple

T646366
Position Surface form Disambiguated ID Type / Status
Subject John Mara E11249 entity
Predicate relative P37 FINISHED
Object Rooney Mara E63855 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: Rooney Mara | Statement: [John Mara, relative, Rooney Mara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rooney Mara
Context triple: [John Mara, relative, Rooney Mara]
  • A. Rooney Mara chosen
    Rooney Mara is an American actress known for her acclaimed performances in films such as "The Girl with the Dragon Tattoo" and "Carol."
  • B. Carmen Ejogo
    Carmen Ejogo is a British actress and singer known for her versatile film and television roles, including her acclaimed portrayal of Coretta Scott King in the historical drama "Selma."
  • C. Olivia Thirlby
    Olivia Thirlby is an American actress known for her roles in films such as "Juno," "Dredd," and various independent and mainstream productions.
  • D. Maggie Siff
    Maggie Siff is an American actress best known for her television roles in series such as Mad Men, Sons of Anarchy, and Billions.
  • E. 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."
  • 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_69a493266a2881909daf4c40f719dee8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49f1b24b08190897d8aedb877bd83 completed March 1, 2026, 8:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69a63742d8a8819087c7c2fa2430da75 completed March 3, 2026, 1:20 a.m.
Created at: March 1, 2026, 7:36 p.m.