Triple

T18942943
Position Surface form Disambiguated ID Type / Status
Subject 近畿大学 E463431 entity
Predicate キャンパス P269 FINISHED
Object 福岡キャンパス — 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: 福岡キャンパス | Statement: [近畿大学, キャンパス, 福岡キャンパス]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 福岡キャンパス
Context triple: [近畿大学, キャンパス, 福岡キャンパス]
  • A. Fukuoka Campus chosen
    Fukuoka Campus is a regional campus of Kindai University located in Fukuoka Prefecture, Japan, offering higher education programs to students in the area.
  • B. Wakayama Campus
    Wakayama Campus is a regional campus of Kindai University in Japan, offering higher education programs and facilities to students in the Wakayama area.
  • C. Iizuka Campus
    Iizuka Campus is one of Kindai University's regional campuses in Japan, hosting various academic programs and facilities for students.
  • D. Nakanoshima Campus
    Nakanoshima Campus is an urban campus of Osaka University located in Osaka’s central Nakanoshima district, housing facilities focused on medicine, life sciences, and related research.
  • E. Yoshida Campus
    Yoshida Campus is the main and historic campus of Kyoto University, located in Kyoto, Japan, and home to many of its core faculties and research facilities.
  • 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_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d3ed847c8190a911a61673608a5c completed April 20, 2026, 7:21 a.m.
Created at: April 10, 2026, 11:59 a.m.