Triple

T10870530
Position Surface form Disambiguated ID Type / Status
Subject Uri E256636 entity
Predicate containsPass P16357 FINISHED
Object Susten Pass E95824 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: Susten Pass | Statement: [Uri, containsPass, Susten Pass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susten Pass
Context triple: [Uri, containsPass, Susten Pass]
  • A. Susten Pass chosen
    Susten Pass is a high mountain pass in the Swiss Alps known for its scenic road connecting the cantons of Bern and Uri.
  • B. Theodul Pass
    Theodul Pass is a high mountain pass in the Alps that connects Switzerland and Italy near the Matterhorn, serving as an important historical and hiking route across the Pennine Alps.
  • C. Flüela Pass
    Flüela Pass is a high mountain pass in the Swiss Alps that connects Davos with the Lower Engadine, known for its scenic alpine landscapes and popular driving and cycling route.
  • D. Fedaia Pass
    Fedaia Pass is a high mountain pass in the Dolomites of northern Italy, known for its scenic views near the Marmolada massif and its importance for alpine tourism and cycling.
  • E. Gerlos Pass
    Gerlos Pass is a high mountain pass in the Austrian Alps that serves as a scenic route connecting the Zillertal valley with the Salzburg region.
  • 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_69d6aa83d1448190a66d93c32394d21f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7518610e48190bee50db71ae0ca3e completed April 9, 2026, 7:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69e23b8b3fd48190b36e34dc19fa5193 completed April 17, 2026, 1:54 p.m.
Created at: April 8, 2026, 9:20 p.m.