Triple

T19555322
Position Surface form Disambiguated ID Type / Status
Subject Sandefjord Fotball E489291 entity
Predicate hasRival P1375 FINISHED
Object FK Tønsberg
FK Tønsberg is a Norwegian football club based in Tønsberg that competes in the lower divisions of the national league system.
E1384002 NE FINISHED

How this triple was built (4 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: FK Tønsberg | Statement: [Sandefjord Fotball, hasRival, FK Tønsberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FK Tønsberg
Context triple: [Sandefjord Fotball, hasRival, FK Tønsberg]
  • A. FK Haugesund
    FK Haugesund is a Norwegian professional football club based in Haugesund that competes in the country’s top divisions and is known for its regional rivalry with Viking FK.
  • B. Bryne FK
    Bryne FK is a Norwegian football club known for developing striker Erling Haaland in its youth system.
  • C. Sarpsborg 08 FF
    Sarpsborg 08 FF is a Norwegian professional football club based in Sarpsborg that competes in the country’s top division, the Eliteserien.
  • D. Hønefoss BK
    Hønefoss BK is a Norwegian football club based in Hønefoss that has competed in the country’s top divisions.
  • E. 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.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: FK Tønsberg
Triple: [Sandefjord Fotball, hasRival, FK Tønsberg]
Generated description
FK Tønsberg is a Norwegian football club based in Tønsberg that competes in the lower divisions of the national league system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: FK Tønsberg
Target entity description: FK Tønsberg is a Norwegian football club based in Tønsberg that competes in the lower divisions of the national league system.
  • A. FK Haugesund
    FK Haugesund is a Norwegian professional football club based in Haugesund that competes in the country’s top divisions and is known for its regional rivalry with Viking FK.
  • B. Bryne FK
    Bryne FK is a Norwegian football club known for developing striker Erling Haaland in its youth system.
  • C. Sarpsborg 08 FF
    Sarpsborg 08 FF is a Norwegian professional football club based in Sarpsborg that competes in the country’s top division, the Eliteserien.
  • D. Hønefoss BK
    Hønefoss BK is a Norwegian football club based in Hønefoss that has competed in the country’s top divisions.
  • E. 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.
  • F. None of above. chosen

Provenance (5 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d335f888190abfc5ba974d3c65e completed April 20, 2026, 2:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07577e66c4819080298e223c2ece16 completed May 15, 2026, 5:27 p.m.
NEDg Description generation batch_6a07583fc26481908bd2f00c19f3b4cd completed May 15, 2026, 5:30 p.m.
NED2 Entity disambiguation (via description) batch_6a07594a23ac81908807df4605555d3f completed May 15, 2026, 5:35 p.m.
Created at: April 10, 2026, 1:42 p.m.