Triple

T20550385
Position Surface form Disambiguated ID Type / Status
Subject Zoe (film) E504580 entity
Predicate producer P490 FINISHED
Object Michael Pruss 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: Michael Pruss | Statement: [Zoe (film), producer, Michael Pruss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Pruss
Context triple: [Zoe (film), producer, Michael Pruss]
  • A. Michael A. Pruss chosen
    Michael A. Pruss is a film producer known for his work on critically acclaimed dramas, including collaborations with major directors on projects such as "Empire of Light."
  • B. Michaël Pruss
    Michaël Pruss is a film and television producer known for his work on high-profile international projects, including the espionage drama series "Berlin Station."
  • C. Michael Grunst
    Michael Grunst is a German local politician who serves as the borough mayor of Berlin’s Lichtenberg district.
  • D. Erich Klein
    Erich Klein was the son of influential psychoanalyst Melanie Klein, about whom relatively little is documented beyond his familial connection.
  • E. Michael Engelhart
    Michael Engelhart was an architect known for his role in the post-war reconstruction of Vienna’s historic Burgtheater.
  • 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_69e0b4b52c048190952b4d0f430813a3 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a5d739bc8190b2bf60f82d2ade0c completed April 20, 2026, 10:16 p.m.
Created at: April 16, 2026, 11:38 a.m.