Triple

T9540721
Position Surface form Disambiguated ID Type / Status
Subject Kelheim (district) E230148 entity
Predicate containsTown P847 FINISHED
Object Kelheim E246167 NE FINISHED

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: Kelheim | Statement: [Kelheim (district), containsTown, Kelheim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelheim
Context triple: [Kelheim (district), containsTown, Kelheim]
  • A. Kelheim chosen
    Kelheim is a historic town in southeastern Germany known for its location at the confluence of the Danube and Altmühl rivers and its proximity to the Danube Gorge and the Befreiungshalle monument.
  • B. Heiderhof
    Heiderhof is a residential subdistrict of the Bonn borough Bad Godesberg in western Germany.
  • C. Kölzig
    Kölzig is the surname of former professional ice hockey goaltender Olie Kolzig, best known for his long NHL career with the Washington Capitals.
  • D. Baltschieder
    Baltschieder is a small Swiss municipality in the canton of Valais, located in the Upper Valais region of the Alps.
  • E. Bardenbach
    Bardenbach is a village and district of the town of Wadern in the Saarland region of western Germany.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca847b1b3081908f72bc932c17cc41 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98e695948190ab107fff38c57de7 completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1eab0860c819091b0169f82eac47f completed April 5, 2026, 4:53 a.m.
Created at: March 30, 2026, 8:01 p.m.