Triple

T21784747
Position Surface form Disambiguated ID Type / Status
Subject Lummen E537805 entity
Predicate locatedNear P294 FINISHED
Object Diest 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: Diest | Statement: [Lummen, locatedNear, Diest]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diest
Context triple: [Lummen, locatedNear, Diest]
  • A. Diest chosen
    Diest is a historic city in Belgium known for its well-preserved medieval center, beguinage, and role as a former residence of the House of Orange-Nassau.
  • B. Turnhout
    Turnhout is a historic city in northern Belgium known for its playing card industry, cultural heritage, and role as a regional center in the Kempen area.
  • C. Nunspeet
    Nunspeet is a Dutch town and municipality on the Veluwe known for its forests, heathlands, and role as a popular nature and holiday destination.
  • D. Driesen
    Driesen is a historic town in the Neumark region of former eastern Brandenburg, now located in western Poland under the name Drezdenko.
  • E. Deurne
    Deurne is a municipality in the Dutch province of North Brabant, known for its rural character and historic peat extraction areas.
  • 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_69e0c47198f881908cb0d237266c10e9 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f04630f4f08190910b9e499a4249ca completed April 28, 2026, 5:31 a.m.
Created at: April 16, 2026, 6:52 p.m.