Triple

T15377802
Position Surface form Disambiguated ID Type / Status
Subject Agent Whiskey E367713 entity
Predicate createdBy P806 FINISHED
Object Jane Goldman E48817 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: Jane Goldman | Statement: [Agent Whiskey, createdBy, Jane Goldman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jane Goldman
Context triple: [Agent Whiskey, createdBy, Jane Goldman]
  • A. Jane Goldman chosen
    Jane Goldman is a British screenwriter, author, and producer known for co-writing hit films such as "Kick-Ass," "X-Men: First Class," and "Kingsman: The Secret Service."
  • B. Jenny Goldman
    Jenny Goldman is the daughter of American playwright and screenwriter James Goldman, known for works such as "The Lion in Winter."
  • C. Ann Goldstein
    Ann Goldstein is an American literary translator best known for bringing Elena Ferrante’s Neapolitan novels and other major works of Italian literature into English.
  • D. Lena Goldman
    Lena Goldman was the wife of prominent New Jersey attorney and politician David T. Wilentz, noted for her role within a well-known American Jewish political family.
  • E. Ruby Goldstein
    Ruby Goldstein was a prominent American boxing referee and former fighter known for officiating major bouts in the mid-20th century.
  • 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_69d85a1551a08190ba2caea7cd51c639 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e5ece1081908d7c1289258b9c1f completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b56dd1c81909a3933330e85fe0e completed May 9, 2026, 10:24 a.m.
Created at: April 10, 2026, 3:18 a.m.