Triple

T15889694
Position Surface form Disambiguated ID Type / Status
Subject Harstad harbour E385283 entity
Predicate locatedIn P40 FINISHED
Object Harstad 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: Harstad | Statement: [Harstad harbour, locatedIn, Harstad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harstad
Context triple: [Harstad harbour, locatedIn, Harstad]
  • A. Harstad chosen
    Harstad is a coastal town and municipality in Troms county, known as an important regional center in Northern Norway with a strong maritime and cultural heritage.
  • B. Kristinestad
    Kristinestad is a small coastal town in western Finland known for its well-preserved wooden old town and historic maritime character.
  • C. Tonstad
    Tonstad is a small village in Agder county, Norway, serving as the administrative and commercial center of Sirdal municipality.
  • D. Harstad municipality
    Harstad municipality is a local government area in Troms county, northern Norway, centered on the coastal town of Harstad and known for its maritime industries and Arctic landscape.
  • E. Stavern
    Stavern is a small coastal town in southern Norway known for its historic fortress, maritime heritage, and role as a popular summer holiday destination.
  • 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_69d86da5b800819083a31be937d738b0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1561d5c28819094c3541d917a4433 completed April 16, 2026, 9:35 p.m.
Created at: April 10, 2026, 4:51 a.m.