Triple

T17842824
Position Surface form Disambiguated ID Type / Status
Subject Madison River E445575 entity
Predicate crosses P416 FINISHED
Object Hebgen Lake 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: Hebgen Lake | Statement: [Madison River, crosses, Hebgen Lake]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hebgen Lake
Context triple: [Madison River, crosses, Hebgen Lake]
  • A. Hebgen Lake chosen
    Hebgen Lake is a large reservoir in southwestern Montana known for its scenic recreation opportunities and its association with the 1959 Hebgen Lake earthquake.
  • B. Mowich Lake
    Mowich Lake is a large, high-elevation glacial lake in Washington State known for its clear waters, scenic mountain views, and access to popular hiking and camping areas.
  • C. Sawtooth Lake
    Sawtooth Lake is a popular high-elevation alpine lake in Idaho known for its clear waters and dramatic mountain scenery.
  • D. Bighorn Lake
    Bighorn Lake is a large reservoir on the Bighorn River, spanning parts of Montana and Wyoming and known for its dramatic canyon scenery and recreational opportunities.
  • E. Mormon Lake
    Mormon Lake is a high-elevation natural lake and seasonal wetland in northern Arizona known for its variable water levels, surrounding ponderosa pine forests, and recreational opportunities.
  • 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_69d8b9f1a6d881909f024bc603111cdb completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48ff8730881908cc8e1b572fa0af8 completed April 19, 2026, 8:19 a.m.
Created at: April 10, 2026, 10:16 a.m.