Triple

T23133807
Position Surface form Disambiguated ID Type / Status
Subject Olst-Wijhe E577253 entity
Predicate hasPart P35 FINISHED
Object Olst 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: Olst | Statement: [Olst-Wijhe, hasPart, Olst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Olst
Context triple: [Olst-Wijhe, hasPart, Olst]
  • A. Olst chosen
    Olst is a village in the Dutch province of Overijssel, situated along the river IJssel and known for its rural character and historic estates.
  • B. Vilsteren
    Vilsteren is a small rural hamlet in the Dutch province of Overijssel, known for its historic estates and scenic landscape along the river Vecht.
  • C. Leven
    Leven is a coastal town in eastern Scotland, situated on the Firth of Forth in the council area of Fife.
  • D. Bruinisse
    Bruinisse is a fishing village and tourist destination in the Dutch province of Zeeland, known for its mussel industry and location on the Grevelingen.
  • E. Oldeelva
    Oldeelva is a river in Norway’s Oldedalen valley, known for its glacial origins and scenic surroundings.
  • 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_69e245f7b0e481909c473ff4e6a54e2c completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e89cce881908727a94dbc00e031 completed April 29, 2026, 4:52 a.m.
Created at: April 17, 2026, 4 p.m.