Triple

T19642767
Position Surface form Disambiguated ID Type / Status
Subject Johann Hartmann E471580 entity
Predicate employer P7 FINISHED
Object Royal Danish Theatre 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: Royal Danish Theatre | Statement: [Johann Hartmann, employer, Royal Danish Theatre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Royal Danish Theatre
Context triple: [Johann Hartmann, employer, Royal Danish Theatre]
  • A. Royal Danish Theatre chosen
    The Royal Danish Theatre is Denmark’s national performing arts institution in Copenhagen, renowned for its historic stages hosting opera, ballet, drama, and classical music.
  • B. Frederiksberg Theatre
    Frederiksberg Theatre is a historic performing arts venue located in the Frederiksberg district of Copenhagen, Denmark.
  • C. Odense Theatre
    Odense Theatre is a historic Danish playhouse in the city of Odense, known for staging a wide repertoire of classical and contemporary performances.
  • D. Aarhus Theatre
    Aarhus Theatre is a prominent historic playhouse and cultural landmark in Aarhus, Denmark, known for staging a wide range of theatrical performances.
  • E. Nyborg Theatre
    Nyborg Theatre is a cultural venue in the Danish town of Nyborg, hosting theatrical performances and other performing arts events.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64122d9f48190961c4b460256f9e7 completed April 20, 2026, 3:07 p.m.
Created at: April 10, 2026, 1:44 p.m.