Triple

T5293975
Position Surface form Disambiguated ID Type / Status
Subject Kundun E119809 entity
Predicate producer P490 FINISHED
Object Barbara De Fina E461960 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: Barbara De Fina | Statement: [Kundun, producer, Barbara De Fina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara De Fina
Context triple: [Kundun, producer, Barbara De Fina]
  • A. Barbara De Fina chosen
    Barbara De Fina is an American film producer best known for her frequent collaborations with director Martin Scorsese on acclaimed films throughout the 1980s and 1990s.
  • B. Denise Di Novi
    Denise Di Novi is an American film producer known for her work on numerous popular films, including several Tim Burton projects and acclaimed literary adaptations.
  • C. Sylvia Abate
    Sylvia Abate is known primarily as the wife of American special effects makeup artist and filmmaker Rick Baker.
  • D. Anita Barone
    Anita Barone is an American actress known for her work in television sitcoms and comedy series, including roles on shows like Friends and The War at Home.
  • E. Laura Martinozzi
    Laura Martinozzi was an Italian noblewoman and duchess of Modena, a niece of Cardinal Mazarin and a politically influential figure in 17th-century Italy.
  • 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_69bd446f22b88190b6a47fb91c68a3e7 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd84f034f081908027a43120b6e122 completed March 20, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21b22be08190ad5d3d6b12b80bcb completed March 21, 2026, 10:54 p.m.
Created at: March 20, 2026, 1:52 p.m.