Triple

T20699162
Position Surface form Disambiguated ID Type / Status
Subject Kolding River E508732 entity
Predicate hasNameInLanguage P15 FINISHED
Object da:Kolding Å 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: da:Kolding Å | Statement: [Kolding River, hasNameInLanguage, da:Kolding Å]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: da:Kolding Å
Context triple: [Kolding River, hasNameInLanguage, da:Kolding Å]
  • 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. Koldingen
    Koldingen is a village and district of the town of Pattensen in Lower Saxony, Germany.
  • C. Aarhus Å
    Aarhus Å is a small river running through the Danish city of Aarhus before emptying into Aarhus Bay.
  • D. Kolding railway station
    Kolding railway station is the main train station in the Danish city of Kolding, serving as a regional and intercity rail hub in southern Jutland.
  • E. Kolding Fjord
    Kolding Fjord is a scenic inlet of the Little Belt in southeastern Jutland, Denmark, known for its sheltered waters, natural landscapes, and the coastal city of Kolding along its shores.
  • 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.