Triple

T22153906
Position Surface form Disambiguated ID Type / Status
Subject Liemers E547483 entity
Predicate contains P35 FINISHED
Object Westervoort 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: Westervoort | Statement: [Liemers, contains, Westervoort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Westervoort
Context triple: [Liemers, contains, Westervoort]
  • A. Westervoort chosen
    Westervoort is a small Dutch municipality in the province of Gelderland, situated near the city of Arnhem along the Rhine.
  • B. Heverlee
    Heverlee is a suburb of Leuven in the Flemish Brabant province of Belgium, known for its residential areas, green spaces, and nearby university facilities.
  • C. Wageningers
    Wageningers are the inhabitants or natives of Wageningen, a city in the province of Gelderland in the Netherlands known for its agricultural university.
  • D. Winschoten
    Winschoten is a town in the northeast of the Netherlands known historically as a regional trade center and for its traditional windmills and Jewish heritage.
  • E. van Berkel
    van Berkel is a Dutch surname most notably associated with architect Ben van Berkel, co-founder of the architecture firm UNStudio.
  • 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.