Triple

T10142783
Position Surface form Disambiguated ID Type / Status
Subject Kumamoto Airport E231626 entity
Predicate hasNativeName P1435 FINISHED
Object 熊本空港 E231626 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: 熊本空港 | Statement: [Kumamoto Airport, hasNativeName, 熊本空港]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 熊本空港
Context triple: [Kumamoto Airport, hasNativeName, 熊本空港]
  • A. Kumamoto Airport chosen
    Kumamoto Airport is a regional and domestic airport in Kumamoto Prefecture, Japan, serving as a key air gateway to the Kyushu region.
  • B. Miyazaki Airport
    Miyazaki Airport is a regional airport in Miyazaki Prefecture, Japan, serving domestic flights and limited international routes for the city and surrounding area.
  • C. 天草飛行場
    天草飛行場は、熊本県天草市に位置し、地域路線を中心に運航する天草エアラインの拠点となっている地方空港です。
  • D. Ōita Airport
    Ōita Airport is a regional Japanese airport in Ōita Prefecture that serves domestic flights and connects the area to major cities such as Tokyo and Osaka.
  • E. Takamatsu Airport
    Takamatsu Airport is a regional international airport in Kagawa Prefecture on Japan’s Shikoku island, serving as the main air gateway to the city of Takamatsu and its surrounding area.
  • 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_69ca848364f881908a24366a6feec1db completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdeb273fec8190818707167e031d58 completed April 2, 2026, 4:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2e60e51488190a6097837eb3ce18a completed April 5, 2026, 10:45 p.m.
Created at: March 30, 2026, 9:07 p.m.