Triple

T9283973
Position Surface form Disambiguated ID Type / Status
Subject The Lost Honour of Katharina Blum E223138 entity
Predicate castMember P1668 FINISHED
Object Heinz Bennent E792415 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: Heinz Bennent | Statement: [The Lost Honour of Katharina Blum, castMember, Heinz Bennent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heinz Bennent
Context triple: [The Lost Honour of Katharina Blum, castMember, Heinz Bennent]
  • A. Heinz Bennent chosen
    Heinz Bennent was a German actor known for his nuanced performances in European cinema and television, including prominent roles in psychologically intense dramas.
  • B. Heinz Alleman
    Heinz Alleman is a mountaineer known for making the first recorded ascent of Mount Deborah in the Alaska Range.
  • C. Winston Hibler
    Winston Hibler was an American screenwriter, producer, and narrator best known for his long association with Walt Disney Studios, where he contributed to classic animated features and nature documentaries.
  • D. Don Brochu
    Don Brochu is a film editor best known for his work on major Hollywood movies, including the hit thriller "The Bodyguard."
  • E. Harold Flender
    Harold Flender was an American writer and screenwriter known for his work in film and television, including contributions to socially conscious projects 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_69ca842123588190b3f2e1a69037d141 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd081e72988190917f425e64631837 completed April 1, 2026, 11:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0f38f99b88190bb979bf9255c07d7 completed April 4, 2026, 11:18 a.m.
Created at: March 30, 2026, 7:34 p.m.