Triple

T22522038
Position Surface form Disambiguated ID Type / Status
Subject Battle of Vågen E556804 entity
Predicate bodyOfWater P1778 FINISHED
Object Vågen harbour 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: Vågen harbour | Statement: [Battle of Vågen, bodyOfWater, Vågen harbour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vågen harbour
Context triple: [Battle of Vågen, bodyOfWater, Vågen harbour]
  • A. Vågen harbour chosen
    Vågen harbour is the central bay and historic waterfront area of Bergen, Norway, around which the city’s old trading quarter and port activities developed.
  • B. Stø harbour
    Stø harbour is a small fishing and tourist port in the village of Stø in Øksnes Municipality, Nordland county, Norway, known as a base for coastal fishing and whale-watching trips.
  • C. Drelnes harbour
    Drelnes harbour is a small coastal port facility serving the village of Drelnes, providing local maritime access and mooring for boats.
  • D. Solva harbour
    Solva harbour is a picturesque tidal inlet and small port village on the Pembrokeshire coast of Wales, known for its colorful waterfront, coastal walks, and boating.
  • E. Langevåg harbour
    Langevåg harbour is a small coastal port in Langevåg, Norway, serving local maritime traffic, fishing vessels, and leisure boats.
  • 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_69e11e5657e881909f16ca58352c50da completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15e32b8a88190ac335d4298dd5ee3 completed April 29, 2026, 1:26 a.m.
Created at: April 16, 2026, 8:50 p.m.