Triple

T22789342
Position Surface form Disambiguated ID Type / Status
Subject Hallenberg E564064 entity
Predicate hasSubdivision P747 FINISHED
Object Liesen 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: Liesen | Statement: [Hallenberg, hasSubdivision, Liesen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liesen
Context triple: [Hallenberg, hasSubdivision, Liesen]
  • A. Liesen chosen
    Liesen is a small village in the Hochsauerland region of North Rhine-Westphalia, Germany, known for its rural setting and proximity to the town of Hallenberg.
  • B. Leissigen
    Leissigen is a Swiss village in the canton of Bern, known for its scenic location in the Bernese Oberland on the shores of Lake Thun.
  • C. Líšina
    Líšina is a small village in the Plzeň Region of the Czech Republic, situated within the administrative area of the Plzeň-South District.
  • D. Liepe
    Liepe is a small municipality in the district of Barnim in the German state of Brandenburg.
  • E. Vohenstrauß
    Vohenstrauß is a small town in the Upper Palatinate region of Bavaria, Germany, known for its historic architecture and surrounding forested landscapes.
  • 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_69e2455500788190b4b33030461f3bbd completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17c3488708190812f7d2edac92184 completed April 29, 2026, 3:34 a.m.
Created at: April 17, 2026, 3:29 p.m.