Triple

T8959331
Position Surface form Disambiguated ID Type / Status
Subject Saving Mr. Banks E213557 entity
Predicate screenwriter P2831 FINISHED
Object Sue Smith E213557 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: Sue Smith | Statement: [Saving Mr. Banks, screenwriter, Sue Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sue Smith
Context triple: [Saving Mr. Banks, screenwriter, Sue Smith]
  • A. Sue Smith chosen
    Sue Smith is an Australian screenwriter known for her work on film and television, including co-writing the screenplay for "Saving Mr. Banks."
  • B. Sue Jones
    Sue Jones is the mother of acclaimed singer-songwriter and pianist Norah Jones.
  • C. Sue Wilson
    Sue Wilson is a key fictional political aide who serves as the hyper-competent personal assistant and scheduler to Vice President (later President) Selina Meyer on the television series "Veep."
  • D. Sue Bayliss
    Sue Bayliss is a supporting character in Arthur Miller’s play "All My Sons," depicted as a cynical, practical neighbor whose attitudes contrast with the idealism of other characters.
  • E. Karen Smith
    Karen Smith is a British television producer best known for creating the hit dance competition series "Strictly Come Dancing."
  • 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_69ca8399ad2081909f8fa41d4314c215 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc672b12b48190a9d964f79b96d237 completed April 1, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc946a2f88190b7cd0fca67d31dfd completed April 3, 2026, 2:05 p.m.
Created at: March 30, 2026, 7 p.m.