Triple

T1458707
Position Surface form Disambiguated ID Type / Status
Subject Maritime Alps E31457 entity
Predicate hasPass P11208 FINISHED
Object Col de Tende E33386 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: Col de Tende | Statement: [Maritime Alps, hasPass, Col de Tende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Col de Tende
Context triple: [Maritime Alps, hasPass, Col de Tende]
  • A. Col de Tende chosen
    Col de Tende is a historic Alpine mountain pass in the Maritime Alps that serves as a key transit route between southeastern France and northwestern Italy.
  • B. Col du Mont Cenis
    Col du Mont Cenis is a high mountain pass in the Alps that historically served as a key transalpine route between France and Italy.
  • C. Col de Montgenèvre
    Col de Montgenèvre is a high mountain pass on the French–Italian border that serves as an important historic route through the Alps, linking the Dauphiné region with the Susa Valley.
  • D. Col de l’Iseran
    Col de l’Iseran is a high mountain pass in the French Alps, known as one of the highest paved passes in Europe and a famous stage on the Tour de France.
  • E. Col de la Givrine
    Col de la Givrine is a mountain pass in the Jura Mountains of western Switzerland, known for its scenic landscapes and cross-country skiing and hiking routes.
  • 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_69a49917dfc081909acdbdf5d684f1ef completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c59c1c288190be08064f2d351b2b completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad4010b8708190ab47d622383d19a6 completed March 8, 2026, 9:23 a.m.
Created at: March 1, 2026, 8 p.m.