Triple

T14732317
Position Surface form Disambiguated ID Type / Status
Subject Lars Hanson E346106 entity
Predicate employer P7 FINISHED
Object Dramaten E360525 NE FINISHED

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: Dramaten | Statement: [Lars Hanson, employer, Dramaten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dramaten
Context triple: [Lars Hanson, employer, Dramaten]
  • A. Västerbotten Theatre
    Västerbotten Theatre is a regional Swedish performing arts institution known for producing and touring theatre in northern Sweden, particularly within Västerbotten County.
  • B. Akademietheater
    Akademietheater is a prominent Viennese theater stage associated with the Burgtheater, known for its contemporary and experimental productions.
  • C. Storsjöteatern
    Storsjöteatern is a prominent performing arts theater and cultural venue located in Östersund, Sweden.
  • D. Drammen Theatre
    Drammen Theatre is a prominent cultural venue and historic theatre building in the city of Drammen, Norway, known for hosting a wide range of performing arts events.
  • E. Royal Dramatic Theatre, Stockholm chosen
    The Royal Dramatic Theatre in Stockholm is Sweden’s national stage for spoken drama and one of the country’s most prestigious and historic theatrical institutions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822e5911c8190ba589f957dbd9ba7 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec72ea9348190817efcdaa973d7f7 completed April 14, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb89ea388190b356df74e36023f7 completed May 8, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:29 a.m.