Triple

T19388684
Position Surface form Disambiguated ID Type / Status
Subject Tillet River E485002 entity
Predicate tributaryOf P415 FINISHED
Object Lake Bourget 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: Lake Bourget | Statement: [Tillet River, tributaryOf, Lake Bourget]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lake Bourget
Context triple: [Tillet River, tributaryOf, Lake Bourget]
  • A. Lake Bourget
    Lake Bourget is a large glacial lake in eastern France, renowned for its scenic Alpine setting, biodiversity, and popularity as a destination for boating and outdoor recreation.
  • B. Dayet Aoua Lake
    Dayet Aoua Lake is a scenic freshwater lake in Morocco’s Middle Atlas region, popular for its natural beauty, birdlife, and outdoor recreation.
  • C. Lake of Tunis
    Lake of Tunis is a coastal lagoon near the city of Tunis in Tunisia, historically significant as a natural harbor and ecological wetland area.
  • D. Lac du Bourget chosen
    Lac du Bourget is a large glacial lake in the Savoie region of southeastern France, known for its scenic Alpine setting and popular recreational activities.
  • E. Lac Pavin
    Lac Pavin is a deep, nearly circular volcanic crater lake in France’s Auvergne region, renowned for its meromictic waters and scenic setting.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b425e848190ab5ae8ae0a034fe2 completed April 20, 2026, 12:25 p.m.
Created at: April 10, 2026, 1:36 p.m.