Triple

T21117039
Position Surface form Disambiguated ID Type / Status
Subject Into the White E520325 entity
Predicate castMember P1668 FINISHED
Object David Kross 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: David Kross | Statement: [Into the White, castMember, David Kross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Kross
Context triple: [Into the White, castMember, David Kross]
  • A. David Kross chosen
    David Kross is a German actor best known internationally for his acclaimed performance as the young Michael Berg in the film "The Reader."
  • B. Eric Pleskow
    Eric Pleskow was an Austrian-born American film executive and producer best known for leading major studios and co-founding the influential independent film company Orion Pictures.
  • C. Scott Ehrlich
    Scott Ehrlich is a notable individual recognized for his contributions in his professional field, though specific widely known details about his work are not clearly established from the given information.
  • D. Scott Kroopf
    Scott Kroopf is an American film producer known for his work on numerous Hollywood features, including the science-fiction adventure film "Zathura: A Space Adventure."
  • E. Jeff Kirschenbaum
    Jeff Kirschenbaum is a Hollywood film producer known for working on major studio features, including big-budget family and action movies.
  • 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_69e0b50a623881909c0bbaf4f2c055e7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72106a3b48190a0efa51a74ae21f0 completed April 21, 2026, 7:02 a.m.
Created at: April 16, 2026, 2:55 p.m.