Triple

T19779016
Position Surface form Disambiguated ID Type / Status
Subject Ilves E475082 entity
Predicate homeArena P373 FINISHED
Object Nokia Arena 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: Nokia Arena | Statement: [Ilves, homeArena, Nokia Arena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nokia Arena
Context triple: [Ilves, homeArena, Nokia Arena]
  • A. Nokia Arena chosen
    Nokia Arena is a modern multi-purpose indoor arena in Tampere, Finland, known for hosting major ice hockey games, concerts, and large-scale events.
  • B. AXA Arena
    AXA Arena is a multi-purpose indoor ice hockey arena in Södertälje, Sweden, best known as the home venue of the Södertälje SK ice hockey team.
  • C. Hikvision Arena
    Hikvision Arena is a football stadium in Marijampolė, Lithuania, primarily used as the home ground of local professional club FK Sūduva.
  • D. Hartwall Areena
    Hartwall Areena is a major multi-purpose indoor arena in Helsinki, Finland, best known as a prominent venue for international ice hockey and large-scale entertainment events.
  • E. Siemens Arena
    Siemens Arena is a major multi-purpose indoor sports and entertainment venue in Vilnius, Lithuania, known for hosting basketball games, concerts, and large-scale 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6538230488190b45cd8aaec658f7f completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.