Triple

T20561510
Position Surface form Disambiguated ID Type / Status
Subject MOWAG E504852 entity
Predicate headquartersLocation P62 FINISHED
Object Kreuzlingen 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: Kreuzlingen | Statement: [MOWAG, headquartersLocation, Kreuzlingen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kreuzlingen
Context triple: [MOWAG, headquartersLocation, Kreuzlingen]
  • A. Kreuzlingen chosen
    Kreuzlingen is a Swiss town in the canton of Thurgau, located on the southern shore of Lake Constance near the German border.
  • B. Sulzach
    Sulzach is a small river in Bavaria, Germany, that flows through the town of Feuchtwangen and forms part of the local Franconian river system.
  • C. Chrüzegg
    Chrüzegg is a mountain in the Swiss Prealps, popular for hiking and panoramic views over northeastern Switzerland.
  • D. Aidlingen
    Aidlingen is a small municipality in the German state of Baden-Württemberg, located southwest of Stuttgart amid the scenic landscapes of the Böblingen region.
  • E. Ruhpolding
    Ruhpolding is a Bavarian alpine town in southeastern Germany known for its winter sports facilities, especially biathlon, and its scenic location in the Chiemgau Alps.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a79ec10481909740eb6a08ae2658 completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.