Triple

T15729294
Position Surface form Disambiguated ID Type / Status
Subject Akan Onsen E381298 entity
Predicate near P350 FINISHED
Object Mount Oakan E374539 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: Mount Oakan | Statement: [Akan Onsen, near, Mount Oakan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Oakan
Context triple: [Akan Onsen, near, Mount Oakan]
  • A. Mount Oakan chosen
    Mount Oakan is an active stratovolcano on Japan’s northern island of Hokkaido, known for its conical shape and scenic forests and lakes.
  • B. Mount Rosea
    Mount Rosea is a prominent sandstone peak and popular hiking destination within Victoria, Australia’s Grampians mountain range.
  • C. Mount Doris
    Mount Doris is a lesser-known peak in Tasmania’s Cradle Mountain–Lake St Clair National Park, accessible via the famous Overland Track and valued by bushwalkers for its alpine scenery and views.
  • D. Mount Morris
    Mount Morris is a small city in Genesee County, Michigan, located near Flint and known as a residential community with local schools, parks, and small businesses.
  • E. Mount Oread
    Mount Oread is the prominent hill in Lawrence, Kansas that serves as the main site of the University of Kansas campus.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fb4cc0081909efe330339474017 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82fcb4e4819097bd0591bbcc3b71 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:46 a.m.