Triple

T17786971
Position Surface form Disambiguated ID Type / Status
Subject Yamaguchi Prefecture E444041 entity
Predicate hasCity P316 FINISHED
Object Sanyo-Onoda 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: Sanyo-Onoda | Statement: [Yamaguchi Prefecture, hasCity, Sanyo-Onoda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanyo-Onoda
Context triple: [Yamaguchi Prefecture, hasCity, Sanyo-Onoda]
  • A. Sanyo-Onoda chosen
    Sanyo-Onoda is a coastal industrial city in western Japan known for its cement and chemical industries and its location along the Seto Inland Sea.
  • B. Ebara
    Ebara is a district within Tokyo’s Shinagawa ward, known as a primarily residential area with local shopping streets and traditional neighborhoods.
  • C. Sanyo
    Sanyo is a Japanese electronics brand known for producing a wide range of consumer and industrial electronic products, including televisions, batteries, and home appliances.
  • D. Nihon Kōki
    Nihon Kōki is an early Heian-period Japanese historical chronicle and one of the Six National Histories, covering events following those recorded in the Shoku Nihongi.
  • E. Nissho
    Nissho was a prominent disciple of the Japanese Buddhist monk Nichiren who helped propagate and systematize Nichiren Buddhism.
  • 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_69d8b9ef17708190bdf7e2adbf14ddc2 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e487938418819096016ad717b014e6 completed April 19, 2026, 7:43 a.m.
Created at: April 10, 2026, 10:12 a.m.