Triple

T17691074
Position Surface form Disambiguated ID Type / Status
Subject Gran Zebrù E441027 entity
Predicate nearestTown P350 FINISHED
Object Sulden 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: Sulden | Statement: [Gran Zebrù, nearestTown, Sulden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sulden
Context triple: [Gran Zebrù, nearestTown, Sulden]
  • A. Sulden chosen
    Sulden is a small alpine village and ski resort in South Tyrol, northern Italy, known for its dramatic high-mountain scenery in the Ortler Alps.
  • B. Sulm
    Sulm is a small river in the German state of Baden-Württemberg that flows through the town of Neckarsulm before joining the Neckar.
  • C. Solen
    Solen was a notable warship that took part in the early 17th-century naval conflicts between Sweden and the Polish–Lithuanian Commonwealth.
  • D. Söll
    Söll is a popular Austrian village and ski resort in the Kitzbühel Alps, known for its extensive winter sports facilities and scenic alpine setting.
  • E. Sundvollen
    Sundvollen is a small village in Norway known for its scenic location by Tyrifjorden and as a gateway to popular hiking areas like Krokskogen and viewpoints such as Kongens utsikt.
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4704b43a88190ba29654ca695839e completed April 19, 2026, 6:03 a.m.
Created at: April 10, 2026, 10:03 a.m.