Triple

T2237751
Position Surface form Disambiguated ID Type / Status
Subject Kyodai E49321 entity
Predicate campus P269 FINISHED
Object Uji Campus E46584 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: Uji Campus | Statement: [Kyodai, campus, Uji Campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uji Campus
Context triple: [Kyodai, campus, Uji Campus]
  • A. Uji Campus chosen
    Uji Campus is one of Kyoto University’s main campuses, known for its concentration of advanced science and engineering research institutes in Uji, Kyoto Prefecture, Japan.
  • B. Bumin Campus
    Bumin Campus is one of Dong-A University's main campuses in Busan, South Korea, housing various academic departments and student facilities.
  • C. Komaba Campus
    Komaba Campus is a major campus of the University of Tokyo, known for hosting the College of Arts and Sciences and many first- and second-year undergraduate programs.
  • D. UZA campus
    UZA campus is a major University of Vienna site that hosts natural science faculties, research institutes, and teaching facilities.
  • E. Ito Campus
    Ito Campus is the main and largest campus of Kyushu University in Fukuoka, Japan, known for its modern facilities and expansive, coastal setting.
  • 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_69a88aa84bdc819086df50e9c20b301e completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc096c7748190a545cc9b229bde62 completed March 7, 2026, 6:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b0a9ee881909dee8b0a657b9c73 completed March 9, 2026, 6:39 a.m.
Created at: March 4, 2026, 7:47 p.m.