Triple

T16095947
Position Surface form Disambiguated ID Type / Status
Subject G Men E390484 entity
Predicate musicBy P1952 FINISHED
Object Bernhard Kaun 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: Bernhard Kaun | Statement: [G Men, musicBy, Bernhard Kaun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bernhard Kaun
Context triple: [G Men, musicBy, Bernhard Kaun]
  • A. Bernhard Kaun chosen
    Bernhard Kaun was a German-American composer and orchestrator best known for his work on early Hollywood film scores, particularly in the horror genre.
  • B. Herbert Boeckl
    Herbert Boeckl was a prominent Austrian painter and influential modernist whose expressive, often abstract works helped shape 20th-century Austrian art.
  • C. Werner Kogler
    Werner Kogler is an Austrian Green Party politician who has served as the country’s vice-chancellor and is known for his role in bringing the Greens into a federal governing coalition.
  • D. Franz Kutschera
    Franz Kutschera was a high-ranking SS and Nazi official who served as the brutal SS and Police Leader in occupied Warsaw during World War II.
  • E. Gotthard Graubner
    Gotthard Graubner was a German painter renowned for his abstract color-space works that explored the materiality and depth of color.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1859283008190baac96142b5c7e53 completed April 17, 2026, 12:57 a.m.
Created at: April 10, 2026, 4:59 a.m.