Triple

T2015463
Position Surface form Disambiguated ID Type / Status
Subject Dominique Gisin E43784 entity
Predicate residence P75 FINISHED
Object Engelberg, Switzerland E229325 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: Engelberg, Switzerland | Statement: [Dominique Gisin, residence, Engelberg, Switzerland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Engelberg, Switzerland
Context triple: [Dominique Gisin, residence, Engelberg, Switzerland]
  • A. Engelberg, Switzerland chosen
    Engelberg, Switzerland is a mountain resort village in the Swiss canton of Obwalden, renowned for its skiing, hiking, and alpine scenery.
  • B. Kandersteg
    Kandersteg is a Swiss mountain village and popular tourist resort known for its scenic alpine landscapes, hiking trails, and access to Lake Oeschinen.
  • C. Saas-Fee
    Saas-Fee is a high-altitude Swiss alpine village and ski resort in the Valais Alps, known for its car-free center, extensive glacier skiing, and dramatic mountain scenery.
  • D. Wengen
    Wengen is a car-free Swiss alpine village and popular ski and hiking resort located in the Bernese Oberland region.
  • E. Gstaad
    Gstaad is an upscale Swiss alpine resort village renowned for its luxury hotels, skiing, and exclusive social scene.
  • 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_69a88716e9f08190946313fdc949e3cf completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb8cb16048190bc626685fbb5f707 completed March 7, 2026, 5:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae270a8cd88190a17839c345424ccd completed March 9, 2026, 1:48 a.m.
Created at: March 4, 2026, 7:37 p.m.