Triple

T15297135
Position Surface form Disambiguated ID Type / Status
Subject Tarzan (2013 film) E365688 entity
Predicate producer P490 FINISHED
Object Reinhard Klooss 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: Reinhard Klooss | Statement: [Tarzan (2013 film), producer, Reinhard Klooss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Reinhard Klooss
Context triple: [Tarzan (2013 film), producer, Reinhard Klooss]
  • A. Reinhard Klooss chosen
    Reinhard Klooss is a German film director, screenwriter, and producer best known for his work on animated features such as the 2013 adaptation of Tarzan.
  • B. Giselher Klebe
    Giselher Klebe was a 20th-century German composer best known for his operas and orchestral works, often inspired by literary sources.
  • C. Gerhard Wilck
    Gerhard Wilck was a German Wehrmacht officer best known for commanding the final defense of Aachen during World War II before surrendering the city to Allied forces in 1944.
  • D. Manfred Schnelldorfer
    Manfred Schnelldorfer is a German figure skater best known for winning the men's singles gold medal at the 1964 Winter Olympics.
  • E. Claus Wehlisch
    Claus Wehlisch is a film editor known for his work on feature films, including the romantic comedy-drama "Love, Rosie."
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e036848c1881908fbaaae0216d6d27 completed April 16, 2026, 1:08 a.m.
Created at: April 10, 2026, 3:15 a.m.