Triple

T12337249
Position Surface form Disambiguated ID Type / Status
Subject Broye–Léman region E294120 entity
Predicate hasCapital P204 FINISHED
Object Payerne E275151 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: Payerne | Statement: [Broye–Léman region, hasCapital, Payerne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Payerne
Context triple: [Broye–Léman region, hasCapital, Payerne]
  • A. Payerne chosen
    Payerne is a historic town and municipality in the canton of Vaud, Switzerland, known for its medieval abbey and regional agricultural significance.
  • B. Malchin
    Malchin is a small town in the Mecklenburgische Seenplatte district of Mecklenburg-Vorpommern in northern Germany.
  • C. Palten
    Palten is a river in Austria that serves as a significant tributary of the Enns River in the Styrian region.
  • D. Peggau
    Peggau is a small Austrian town in the state of Styria, known for its scenic location along the Mur River and nearby cave and rock formations.
  • E. Jogne
    Jogne is a river in western Switzerland that flows through the canton of Fribourg before joining the Sarine.
  • 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_69d6ab6ae0dc8190b1522a9c1c55c114 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f6683e881908920e1fee02a14e3 completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62aa5f21c8190bcb32a078a2f7ebb completed May 2, 2026, 4:47 p.m.
Created at: April 8, 2026, 9:53 p.m.