Triple

T18734314
Position Surface form Disambiguated ID Type / Status
Subject Cannstatt E458120 entity
Predicate hasLandmark P105 FINISHED
Object Kurpark Bad Cannstatt 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: Kurpark Bad Cannstatt | Statement: [Cannstatt, hasLandmark, Kurpark Bad Cannstatt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurpark Bad Cannstatt
Context triple: [Cannstatt, hasLandmark, Kurpark Bad Cannstatt]
  • A. Kurpark Bad Cannstatt chosen
    Kurpark Bad Cannstatt is a historic spa and recreation park in Stuttgart’s Bad Cannstatt district, known for its mineral springs, landscaped gardens, and leisure facilities.
  • B. Kurpark Baden
    Kurpark Baden is a historic spa park in Baden bei Wien, Austria, known for its landscaped gardens, walking paths, and cultural events.
  • C. Kurpark Bad Godesberg
    Kurpark Bad Godesberg is a historic spa and landscape park in the Bonn district of Bad Godesberg, known for its landscaped gardens, walking paths, and cultural events.
  • D. Kurpark Bad Nauheim
    Kurpark Bad Nauheim is a historic spa park in the German town of Bad Nauheim, known for its landscaped gardens, Art Nouveau architecture, and therapeutic saline facilities.
  • E. Sindelfingen Park
    Sindelfingen Park is a public green space in the town of Dronfield, England, offering recreational areas and natural scenery for local residents and visitors.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d7a06788190a8e09c657aaeb8e5 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:51 a.m.