Triple

T18219570
Position Surface form Disambiguated ID Type / Status
Subject Komische Oper Berlin E436256 entity
Predicate formerDirector P10190 FINISHED
Object Andreas Homoki 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: Andreas Homoki | Statement: [Komische Oper Berlin, formerDirector, Andreas Homoki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andreas Homoki
Context triple: [Komische Oper Berlin, formerDirector, Andreas Homoki]
  • A. Andreas Homoki chosen
    Andreas Homoki is a prominent Swiss opera director and cultural manager, known for leading major European opera houses and shaping contemporary opera productions.
  • B. Andréas Strauss
    Andréas Strauss is an Austrian designer and artist known for his experimental, often sustainable and socially engaged design projects.
  • C. Andreas Gropa
    Andreas Gropa was a 14th-century Albanian nobleman who held significant regional power in the Balkans as a feudal lord.
  • D. Stefan Hatos
    Stefan Hatos was an American television producer and writer best known for co-creating and producing the long-running game show "Let's Make a Deal."
  • E. Viktor Kassai
    Viktor Kassai is a Hungarian football referee renowned for officiating high-profile international matches, including major UEFA and FIFA tournaments.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47a3b1c8190919e954089b41ae0 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.