Triple

T20720727
Position Surface form Disambiguated ID Type / Status
Subject Lofoten Escarpment E509302 entity
Predicate locatedOffCoastOf P212 FINISHED
Object Lofoten 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: Lofoten | Statement: [Lofoten Escarpment, locatedOffCoastOf, Lofoten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lofoten
Context triple: [Lofoten Escarpment, locatedOffCoastOf, Lofoten]
  • A. Lofoten chosen
    Lofoten is a dramatic Arctic archipelago in Norway known for its steep mountains, sheltered bays, fishing villages, and views of the midnight sun and Northern Lights.
  • B. Vesterålen
    Vesterålen is a scenic archipelago in northern Norway known for its dramatic coastal landscapes, rich fishing traditions, and excellent whale-watching opportunities.
  • C. Hamarøy
    Hamarøy is a coastal municipality in Nordland county, Norway, known for its dramatic fjord and mountain landscapes and its association with author Knut Hamsun.
  • D. Ålesund archipelago
    The Ålesund archipelago is a coastal island group in western Norway known for its scenic seascapes, fishing communities, and proximity to the Art Nouveau town of Ålesund.
  • E. Andøya
    Andøya is a large Norwegian island in Nordland county, known for its dramatic coastal landscapes, space center, and rich bird and whale-watching opportunities.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1d5eec08190832ffba8a90f3076 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:26 p.m.