Triple

T23386745
Position Surface form Disambiguated ID Type / Status
Subject Gemen Castle E593903 entity
Predicate isLocatedNear P350 FINISHED
Object Borken town centre 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: Borken town centre | Statement: [Gemen Castle, isLocatedNear, Borken town centre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Borken town centre
Context triple: [Gemen Castle, isLocatedNear, Borken town centre]
  • A. Borken chosen
    Borken is a town in western Germany that serves as an administrative and commercial center in the state of North Rhine-Westphalia.
  • B. Bonn pedestrian shopping zone
    The Bonn pedestrian shopping zone is a central car-free area in Bonn known for its dense concentration of shops, cafés, and street life.
  • C. Stadtmitte
    Stadtmitte is the central urban district and main downtown area of the town of Eberswalde in Germany.
  • D. Stadtmitte
    Stadtmitte is a central Berlin U-Bahn station serving as an important interchange and access point to the city’s historic Mitte district.
  • E. Stadtmitte
    Stadtmitte is the central urban district of the town of Bad Honnef in North Rhine-Westphalia, Germany.
  • 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_69e25d2754fc819085deea939bde60ab completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a498fd08819085e90a872d9d0c7a completed April 29, 2026, 6:26 a.m.
Created at: April 17, 2026, 5:35 p.m.