Triple

T15302462
Position Surface form Disambiguated ID Type / Status
Subject Viking FK E365821 entity
Predicate rival P437 FINISHED
Object Sandnes Ulf E720094 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: Sandnes Ulf | Statement: [Viking FK, rival, Sandnes Ulf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandnes Ulf
Context triple: [Viking FK, rival, Sandnes Ulf]
  • A. Sandnes Ulf chosen
    Sandnes Ulf is a Norwegian football club from Sandnes, known for competing in the national league system and for its local rivalries in Rogaland.
  • B. Sandefjord Fotball
    Sandefjord Fotball is a Norwegian professional football club based in the town of Sandefjord, known for competing in the country’s top divisions.
  • C. Vålerenga
    Vålerenga is a neighborhood in Oslo, Norway, known for its working-class roots and strong association with the local football club Vålerenga Fotball.
  • D. Tromsø IL
    Tromsø IL is a Norwegian professional football club based in the city of Tromsø, known for competing in the country’s top divisions and for being one of the world’s northernmost elite clubs.
  • E. Strømsgodset
    Strømsgodset is a Norwegian professional football club based in Drammen, best known for competing in the country’s top division, the Eliteserien.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03ccd575c8190aa43262d3b73ef3c completed April 16, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff364bafd0819086b8aab1c216c6fa completed May 9, 2026, 1:27 p.m.
Created at: April 10, 2026, 3:15 a.m.