Triple

T23301735
Position Surface form Disambiguated ID Type / Status
Subject Temple of the Flourishing Law E590319 entity
Predicate hasArtWork P1572 FINISHED
Object Guze Kannon 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: Guze Kannon | Statement: [Temple of the Flourishing Law, hasArtWork, Guze Kannon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guze Kannon
Context triple: [Temple of the Flourishing Law, hasArtWork, Guze Kannon]
  • A. Tachibana Kanade
    Tachibana Kanade is a quiet, enigmatic girl with supernatural abilities who serves as a central figure in the afterlife high school setting of the anime Angel Beats!.
  • B. Takako Kawai
    Takako Kawai is a Japanese mathematician known for her work in algebraic analysis and microlocal analysis.
  • C. Koyasu Kannon chosen
    Koyasu Kannon is a form of the bodhisattva Kannon especially revered in Japan as a protector of pregnancy, safe childbirth, and child-rearing.
  • D. Konekomaru Miwa
    Konekomaru Miwa is a studious and tactically minded young exorcist-in-training from the manga and anime series Blue Exorcist, known for his intelligence, loyalty, and strong sense of duty to his friends.
  • E. Okamura Sayaka
    Okamura Sayaka is a Japanese voice actress and singer known for her work in anime and related media.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d37fd08190ad2d199c54324c02 completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:04 p.m.