Triple

T22150893
Position Surface form Disambiguated ID Type / Status
Subject Bonheiden E547408 entity
Predicate locatedNear P294 FINISHED
Object Keerbergen 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: Keerbergen | Statement: [Bonheiden, locatedNear, Keerbergen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keerbergen
Context triple: [Bonheiden, locatedNear, Keerbergen]
  • A. Keerbergen chosen
    Keerbergen is a municipality in the Flemish Brabant province of Belgium, known for its residential character and green, wooded surroundings.
  • B. Kerkrade
    Kerkrade is a town in the southeastern Netherlands, near the German border, known for its mining history and the international music festival WMC Kerkrade.
  • C. Koudekerke
    Koudekerke is a village in the Dutch province of Zeeland, located near the North Sea coast on the former island of Walcheren.
  • D. Kortenaken
    Kortenaken is a rural municipality in the Flemish Brabant province of Belgium, known for its agricultural landscape and small village communities.
  • E. Harelbeke
    Harelbeke is a municipality in the Belgian province of West Flanders, known for its historic town center and as a regular host of the E3 Saxo Bank Classic cycling race.
  • 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_69e11e3b52088190ad5df386d01eb2fb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129f37dac8190a7cecb12f4271515 completed April 28, 2026, 9:43 p.m.
Created at: April 16, 2026, 8:33 p.m.