Triple

T16448445
Position Surface form Disambiguated ID Type / Status
Subject Bormio E399491 entity
Predicate knownFor P22 FINISHED
Object Gavia Pass E996300 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: Gavia Pass | Statement: [Bormio, knownFor, Gavia Pass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gavia Pass
Context triple: [Bormio, knownFor, Gavia Pass]
  • A. Gavia Pass chosen
    Gavia Pass is a high mountain pass in the Italian Alps, renowned for its challenging, scenic road and frequent inclusion in the Giro d'Italia cycling race.
  • B. Loibl Pass
    Loibl Pass is a mountain pass in the Karawanks range that connects Austria and Slovenia, historically serving as an important transalpine route.
  • C. Roki Pass
    Roki Pass is a high mountain pass in the Greater Caucasus that serves as a key transit route between Georgia and Russia.
  • D. Hirzel Pass
    Hirzel Pass is a mountain pass in Switzerland that connects the Sihl Valley with the Lake Zurich region, serving as a scenic transit route through the hills between Zurich and Zug.
  • E. Ofen Pass
    Ofen Pass is a high mountain pass in the Swiss canton of Graubünden that connects the Engadine valley with the Val Müstair through the Rhaetian Alps.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32cdee44c8190ae0df20c58ff7558 completed April 18, 2026, 7:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004594a4508190be08f3acfff36ab0 completed May 10, 2026, 8:45 a.m.
Created at: April 10, 2026, 5:10 a.m.