Triple

T21313628
Position Surface form Disambiguated ID Type / Status
Subject Carl Ebert E525406 entity
Predicate employer P7 FINISHED
Object Städtische Oper Berlin 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: Städtische Oper Berlin | Statement: [Carl Ebert, employer, Städtische Oper Berlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Städtische Oper Berlin
Context triple: [Carl Ebert, employer, Städtische Oper Berlin]
  • A. Deutsche Oper Berlin chosen
    Deutsche Oper Berlin is one of Germany’s largest and most renowned opera houses, known for its grand productions and modernist architecture in Berlin.
  • B. Berlin State Opera
    The Berlin State Opera is one of Germany’s leading opera houses, renowned for its historic venue, world-class productions, and prominent role in Berlin’s cultural life.
  • C. Hamburg State Opera
    Hamburg State Opera is a major German opera company and historic cultural institution in Hamburg, renowned for its world-class productions and leading international artists.
  • D. Stiftung Oper in Berlin
    Stiftung Oper in Berlin is a public foundation that oversees and manages Berlin’s major opera houses and related cultural institutions.
  • E. Leipzig Opera
    Leipzig Opera is one of Germany’s oldest opera houses, renowned for its rich musical tradition and historic role in the development of European opera.
  • 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_69e0b518b8948190ad69cf9a8784d397 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e75dcc6350819093763632b7e6e4ac completed April 21, 2026, 11:21 a.m.
Created at: April 16, 2026, 4:27 p.m.