Triple

T15558050
Position Surface form Disambiguated ID Type / Status
Subject Haugesund Airport Karmøy E370920 entity
Predicate locatedOn P40 FINISHED
Object island of Karmøy E77362 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: island of Karmøy | Statement: [Haugesund Airport Karmøy, locatedOn, island of Karmøy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: island of Karmøy
Context triple: [Haugesund Airport Karmøy, locatedOn, island of Karmøy]
  • A. Karmøy chosen
    Karmøy is a large island and municipality in Rogaland county, Norway, known for its coastal fishing communities, maritime heritage, and historic Viking sites.
  • B. Storøya island
    Storøya island is a small, remote Arctic island in the Svalbard archipelago of Norway, known for its polar wildlife and harsh, icy environment.
  • C. Rolvsøy island
    Rolvsøy island is a Norwegian island in Østfold county known for its residential communities and proximity to the city of Fredrikstad.
  • D. Storøya
    Storøya is an island located in the lake Tyrifjorden in Norway.
  • E. Langøya
    Langøya is a large island in the Vesterålen archipelago in northern Norway, known for its dramatic coastal landscapes and fishing communities.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04dda3ab88190ab383333ce69fe8f completed April 16, 2026, 2:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe6287f48190a54d0d029dc503f8 completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:09 a.m.