Triple

T23483799
Position Surface form Disambiguated ID Type / Status
Subject Asker municipality E570473 entity
Predicate hasSportsClub P346 FINISHED
Object Frisk Asker Ishockey 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: Frisk Asker Ishockey | Statement: [Asker municipality, hasSportsClub, Frisk Asker Ishockey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frisk Asker Ishockey
Context triple: [Asker municipality, hasSportsClub, Frisk Asker Ishockey]
  • A. Frisk Asker chosen
    Frisk Asker is a Norwegian sports club best known for its ice hockey team, which competes at the top level of Norwegian hockey.
  • B. Storhamar Hockey
    Storhamar Hockey is a professional ice hockey club from Hamar, Norway, known as one of the country’s most successful and storied teams.
  • C. Trondheim HK
    Trondheim HK is a Norwegian handball club based in Trondheim, known for competing in the national handball leagues.
  • D. Asker Fotball
    Asker Fotball is a Norwegian football club based in Asker, known for competing in the national league system and developing local talent.
  • E. Gjøvik Hockey
    Gjøvik Hockey is an ice hockey club based in Gjøvik, Norway, competing in the Norwegian league system.
  • 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a751e6a08190a42c36722275d5d3 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:03 p.m.