Triple

T19206285
Position Surface form Disambiguated ID Type / Status
Subject The Call of the Wild (2020 film) E480241 entity
Predicate producer P490 FINISHED
Object Diana Pokorny 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: Diana Pokorny | Statement: [The Call of the Wild (2020 film), producer, Diana Pokorny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Pokorny
Context triple: [The Call of the Wild (2020 film), producer, Diana Pokorny]
  • A. Diana Pokorny chosen
    Diana Pokorny is a film producer best known for her work on the fantasy adventure movie "Inkheart."
  • B. Paula Cinko
    Paula Cinko is a performer best known for being one of the members of the singing and dancing troupe The Golddiggers, which frequently appeared on television variety shows in the late 1960s and 1970s.
  • C. Gwendolyn Kopechne
    Gwendolyn Kopechne is an individual whose name appears as an alternate or formal version of Gwen Kopechne, likely referring to the same person.
  • D. Mona Pacholska
    Mona Pacholska is a researcher who co-authored the influential 2021 Nature paper by Jumper et al. that introduced the breakthrough AlphaFold protein structure prediction system.
  • E. Catherine Hapka
    Catherine Hapka is an American author known for writing and co-writing numerous children's and young adult books, including equestrian-themed novels.
  • 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_69d8e8cb8c348190b52075823911c869 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5f99d8ad0819098ebd4ee007149f1 completed April 20, 2026, 10:02 a.m.
Created at: April 10, 2026, 1:19 p.m.