Triple

T38631333
Position Surface form Disambiguated ID Type / Status
Subject Isberget E937461 entity
Predicate associatedWithLeagueLevelOfClub P50168 FINISHED
Object Norwegian football league system E245887 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: Norwegian football league system | Statement: [Isberget, associatedWithLeagueLevelOfClub, Norwegian football league system]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: associatedWithLeagueLevelOfClub
Context triple: [Isberget, associatedWithLeagueLevelOfClub, Norwegian football league system]
  • A. associatedLeagueLevel chosen
    Indicates that one entity is linked to another entity representing the competitive tier or level of a sports league.
  • B. supportsClubLeagueLevel
    Indicates that an entity provides backing or resources enabling a club to participate at a specific league level.
  • C. competitionLevelOfOwnedClub
    Indicates the competitive tier or league level at which a club owned by an entity participates.
  • D. associatedWithCompetitionLevel
    Indicates that something has a relationship to, or is characterized by, a particular level or tier of competition.
  • E. associatedClub2
    Indicates that an entity has a secondary or additional affiliation or membership with a particular club.
  • F. None of above.

Provenance (4 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_69f76ed5ca3c81909288f61fbf37b359 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_6a037c9141dc819098d7fcc36e69882c completed May 12, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a41fd590ba88190a8f0618b3e562369 completed June 29, 2026, 5:06 a.m.
PD Predicate disambiguation batch_6a037a2026248190b894436a578d79ac completed May 12, 2026, 7:06 p.m.
Created at: May 3, 2026, 4:32 p.m.