Triple

T22154041
Position Surface form Disambiguated ID Type / Status
Subject Montferland E547486 entity
Predicate containsSettlement P847 FINISHED
Object Beek 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: Beek | Statement: [Montferland, containsSettlement, Beek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beek
Context triple: [Montferland, containsSettlement, Beek]
  • A. Beek
    Beek is a small municipality in the Dutch province of Limburg, known for hosting Maastricht Aachen Airport and its convenient location near the borders with Belgium and Germany.
  • B. Beek chosen
    Beek is a village in the Dutch province of Gelderland, known for its scenic location near the hills and forests of the Nijmegen area.
  • C. Beekkant
    Beekkant is a Brussels Metro station that functions as a key interchange point in the western part of the city’s rapid transit network.
  • D. Zuunbeek
    Zuunbeek is a small stream in Belgium that serves as a right-bank tributary of the River Dender.
  • E. Vierlingsbeek
    Vierlingsbeek is a village in the Dutch province of North Brabant, known for its rural character and location along the river Maas.
  • 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_69f129f6d5b88190badee2e515a3b633 completed April 28, 2026, 9:43 p.m.
Created at: April 16, 2026, 8:33 p.m.