Triple

T3648637
Position Surface form Disambiguated ID Type / Status
Subject Karmøy E77362 entity
Predicate hasCoastlineOn P212 FINISHED
Object Karmsundet E426283 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: Karmsundet | Statement: [Karmøy, hasCoastlineOn, Karmsundet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karmsundet
Context triple: [Karmøy, hasCoastlineOn, Karmsundet]
  • A. Karmsundet chosen
    Karmsundet is a narrow strait in Rogaland county, Norway, separating the island of Karmøy from the mainland and forming part of the historic sailing route along the Norwegian coast.
  • B. Norrsundet
    Norrsundet is a small coastal locality in eastern Sweden known historically for its sawmill and harbor along the Gulf of Bothnia.
  • C. Tjeldsundet
    Tjeldsundet is a narrow strait in northern Norway that separates the islands of Hinnøya and Tjeldøya and connects the Ofotfjorden with the open sea.
  • D. Skudenesfjorden
    Skudenesfjorden is a fjord in Rogaland county, southwestern Norway, lying along the coast by the island municipality of Karmøy and opening into the North Sea.
  • E. Iddefjord
    Iddefjord is a narrow fjord forming part of the border between Norway and Sweden, known for its scenic landscapes and proximity to the town of Halden.
  • 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_69ad85de1b988190a45f8dbfebc806fc completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc38c22548190a271a69fb832a5a8 completed March 8, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5db5d2fcc8190818b79d873cebcf6 completed March 14, 2026, 10:04 p.m.
Created at: March 8, 2026, 3:24 p.m.