Triple

T20699166
Position Surface form Disambiguated ID Type / Status
Subject Kolding E508732 entity
Predicate locatedOn P40 FINISHED
Object Kolding River 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: Kolding River | Statement: [Kolding, locatedOn, Kolding River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kolding River
Context triple: [Kolding, locatedOn, Kolding River]
  • A. Kolding River chosen
    Kolding River is a watercourse in southern Denmark that flows through the city of Kolding before emptying into Kolding Fjord.
  • B. Vejle River
    Vejle River is a Danish watercourse in Jutland known for flowing through the town of Vejle and its surrounding valley before emptying into Vejle Fjord.
  • C. Odense River
    The Odense River is a waterway on the Danish island of Funen that flows through the city of Odense before emptying into Odense Fjord.
  • D. Suså River
    The Suså River is one of Zealand’s largest rivers in Denmark, flowing through the town of Næstved and surrounding countryside before emptying into Karrebæk Fjord.
  • E. Venø
    Venø is a small Danish island in the Limfjord known for its scenic landscapes, birdlife, and traditional coastal village atmosphere.
  • 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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c113e4cc8190aabc11e3f2530e32 completed April 21, 2026, 12:13 a.m.
Created at: April 16, 2026, 12:11 p.m.