Triple

T22804739
Position Surface form Disambiguated ID Type / Status
Subject Mass (2021 film) E564500 entity
Predicate producer P490 FINISHED
Object Fran Kranz 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: Fran Kranz | Statement: [Mass (2021 film), producer, Fran Kranz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fran Kranz
Context triple: [Mass (2021 film), producer, Fran Kranz]
  • A. Fran Kranz chosen
    Fran Kranz is an American actor best known for his roles in the TV series "Dollhouse" and the horror-comedy film "The Cabin in the Woods."
  • B. Christopher Pratt
    Christopher Pratt was a prominent Canadian painter and printmaker known for his precise, contemplative depictions of Atlantic Canadian landscapes and interiors.
  • C. Thomas Sadoski
    Thomas Sadoski is an American actor known for his roles in television series like "The Newsroom" and films such as "John Wick" and "Wild."
  • D. Ben Schwartz
    Ben Schwartz is an American actor, comedian, and voice performer known for roles in projects like Parks and Recreation and for voicing animated characters in films and television.
  • E. Kyle Howard
    Kyle Howard is an American actor best known for his comedic roles in television series and films, including prominent parts in sitcoms.
  • 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17d5b37cc8190a41d8f304ba8d609 completed April 29, 2026, 3:39 a.m.
Created at: April 17, 2026, 3:31 p.m.