Triple

T22212276
Position Surface form Disambiguated ID Type / Status
Subject Go E548980 entity
Predicate starring P1507 FINISHED
Object Sarah Polley 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: Sarah Polley | Statement: [Go, starring, Sarah Polley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Polley
Context triple: [Go, starring, Sarah Polley]
  • A. Sarah Polley chosen
    Sarah Polley is a Canadian actress, writer, and filmmaker known for acclaimed works such as "Away from Her," "Stories We Tell," and the Oscar-winning "Women Talking."
  • B. Rebecca Miller
    Rebecca Miller is an American filmmaker, screenwriter, and novelist known for works such as "Personal Velocity" and "The Private Lives of Pippa Lee."
  • C. Courtney Hunt
    Courtney Hunt is an American filmmaker best known for her acclaimed independent drama "Frozen River," which earned multiple award nominations including an Academy Award for Best Original Screenplay.
  • D. Debra Granik
    Debra Granik is an American filmmaker best known for directing the critically acclaimed independent dramas "Winter's Bone" and "Leave No Trace."
  • E. Abi Morgan
    Abi Morgan is a British playwright and screenwriter known for her work on acclaimed films and television dramas such as "The Iron Lady," "Suffragette," and "The Hour."
  • 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b2c8b608190b0047af4ac91b023 completed April 28, 2026, 9:48 p.m.
Created at: April 16, 2026, 8:36 p.m.