Triple

T18195812
Position Surface form Disambiguated ID Type / Status
Subject municipality of Tholen E435657 entity
Predicate capital P234 FINISHED
Object town of Tholen 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: town of Tholen | Statement: [municipality of Tholen, capital, town of Tholen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: town of Tholen
Context triple: [municipality of Tholen, capital, town of Tholen]
  • A. municipality of Tholen
    The municipality of Tholen is a local government area in the Dutch province of Zeeland that encompasses several islands and towns, including Sint Philipsland and the island of Tholen.
  • B. Tholen chosen
    Tholen is a municipality and town in the Dutch province of Zeeland, located in the southwest of the Netherlands and known for its dikes, polders, and historic center.
  • C. Thorenburg
    Thorenburg is the German name for the Romanian city of Turda, a historic settlement in Transylvania known for its ancient salt mines and medieval heritage.
  • D. Hulten
    Hulten is a small village in the Dutch province of North Brabant, located within the municipality of Gilze en Rijen.
  • E. Hollenstedt
    Hollenstedt is a municipality in Lower Saxony, Germany, located in the district of Harburg southwest of Hamburg.
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d2ad5881909d846f3851ac9ec9 completed April 19, 2026, 2:04 p.m.
Created at: April 10, 2026, 10:31 a.m.