Triple

T15582796
Position Surface form Disambiguated ID Type / Status
Subject Akan Caldera E374540 entity
Predicate near P350 FINISHED
Object Akan Onsen E381298 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: Akan Onsen | Statement: [Akan Caldera, near, Akan Onsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akan Onsen
Context triple: [Akan Caldera, near, Akan Onsen]
  • A. Akan Onsen chosen
    Akan Onsen is a hot spring resort area in eastern Hokkaido, Japan, known for its lakeside setting, traditional ryokan inns, and access to volcanic landscapes within Akan-Mashu National Park.
  • B. Ako Onsen
    Ako Onsen is a coastal hot spring resort area in Ako, Hyōgo Prefecture, Japan, known for its seaside baths and views of the Seto Inland Sea.
  • C. Kaga Onsen
    Kaga Onsen is a renowned hot spring resort area in Ishikawa Prefecture, Japan, famous for its historic ryokan inns, traditional culture, and scenic natural surroundings.
  • D. Zao Onsen
    Zao Onsen is a historic hot spring resort in Japan renowned for its sulfurous baths, ski slopes, and scenic mountain landscapes.
  • E. Hoheikyo Onsen
    Hoheikyo Onsen is a popular hot spring resort near Sapporo known for its large open-air baths set amid natural scenery and its Indian-style curry.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e45ee3c8190a6aee06a5805ca39 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56c3efb48190ad94d9d326c6c2c0 completed May 9, 2026, 3:46 p.m.
Created at: April 10, 2026, 4:11 a.m.