Triple

T22011054
Position Surface form Disambiguated ID Type / Status
Subject Rupel region E543572 entity
Predicate contains P35 FINISHED
Object Rumst 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: Rumst | Statement: [Rupel region, contains, Rumst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rumst
Context triple: [Rupel region, contains, Rumst]
  • A. Rumst chosen
    Rumst is a municipality in the Belgian province of Antwerp, known for its location at the confluence of the rivers Rupel and Nete.
  • B. Rumsen
    Rumsen is a now-extinct Native American language formerly spoken by the Rumsen Ohlone people of the central California coast, traditionally classified within the Costanoan (Ohlone) branch of the Utian language family.
  • C. Rummu
    Rummu is a small settlement in northern Estonia best known for its former limestone quarry and submerged prison complex, which have become a distinctive tourist attraction.
  • D. Rommen
    Rommen is a neighborhood in Oslo, Norway, situated within the Søndre Nordstrand borough.
  • E. Horpmaal
    Horpmaal is a small village in the municipality of Heers in the Belgian province of Limburg.
  • 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_69e11e2db934819095556760c7d85e4d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127a4338c8190836074d21bfbaf78 completed April 28, 2026, 9:33 p.m.
Created at: April 16, 2026, 8:22 p.m.