Triple

T20920331
Position Surface form Disambiguated ID Type / Status
Subject Bungo Province E515189 entity
Predicate locatedIn P40 FINISHED
Object eastern Kyushu 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: eastern Kyushu | Statement: [Bungo Province, locatedIn, eastern Kyushu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: eastern Kyushu
Context triple: [Bungo Province, locatedIn, eastern Kyushu]
  • A. eastern Kyushu chosen
    Eastern Kyushu is the eastern portion of Japan’s Kyushu Island, known for its coastal landscapes, hot spring resorts, and volcanic scenery.
  • B. northern Kyushu
    Northern Kyushu is the historically significant northern part of Japan’s Kyushu Island, known as an early center of trade, culture, and technological exchange with the Asian continent.
  • C. South Kyushu
    South Kyushu is the southern portion of Japan’s Kyushu Island, known for its active volcanoes, hot springs, and subtropical climate.
  • D. Chikuho region
    The Chikuho region is a former coal-mining area in central Fukuoka Prefecture, Japan, known for its industrial history and working-class culture.
  • E. Kōga region
    The Kōga region is a historic area in Japan famed as one of the principal centers of ninja (shinobi) activity alongside Iga.
  • 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_69e0b4f9d5ec8190bb2bd27350ed341c completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6ec677338819081410cbaa2846260 completed April 21, 2026, 3:17 a.m.
Created at: April 16, 2026, 12:48 p.m.