Triple

T1790527
Position Surface form Disambiguated ID Type / Status
Subject The Martian E39484 entity
Predicate castMember P1668 FINISHED
Object Kate Mara E10370 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: Kate Mara | Statement: [The Martian, castMember, Kate Mara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Mara
Context triple: [The Martian, castMember, Kate Mara]
  • A. Kate Mara chosen
    Kate Mara is an American actress known for her roles in films like "The Martian" and "Brokeback Mountain" and TV series such as "House of Cards."
  • B. Zoe Saldana
    Zoe Saldana is an American actress known for her prominent roles in major science fiction and fantasy franchises, including Star Trek, Avatar, and the Marvel Cinematic Universe.
  • C. Robin Ruzan
    Robin Ruzan is an American writer, producer, and actress known for her work in comedy and television, including contributions to projects associated with "Saturday Night Live."
  • D. Maya Hawke
    Maya Hawke is an American actress and singer best known for her breakout role as Robin Buckley in the Netflix series "Stranger Things."
  • E. Rosario Dawson
    Rosario Dawson is an American actress and producer known for her versatile roles in film and television, including performances in "Kids," "Rent," and various Marvel/Netflix series.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa6512804c8190a5743c10bd37f83f completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada9aa10b881909923b8d0f3a30ee6 completed March 8, 2026, 4:54 p.m.
Created at: March 4, 2026, 7:32 p.m.