Triple

T27004607
Position Surface form Disambiguated ID Type / Status
Subject 金光教 E680207 entity
Predicate 創始地 P4560 FINISHED
Object 日本・備中国 LITERAL 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: 日本・備中国 | Statement: [金光教, 創始地, 日本・備中国]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 創始地
Context triple: [金光教, 創始地, 日本・備中国]
  • A. foundingLocationPresentCountry
    Indicates the present-day country in which the location where something (typically an organization or institution) was founded is situated.
  • B. placeFounded chosen
    Indicates the location where an entity (such as an organization or institution) was originally established or founded.
  • C. capitalOfOrigin
    Indicates that one entity is the capital city associated with the origin (such as birthplace, founding place, or source location) of another entity.
  • D. coFoundedIn
    Indicates that two or more entities jointly founded something (such as an organization or company) in a specific place or at a specific time.
  • E. originOfSettlement
    Indicates the place, source, or starting point from which a settlement was established or originated.
  • F. None of above.

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_69eeeb52908c8190bd246244686aa455 completed April 27, 2026, 4:51 a.m.
NER Named-entity recognition batch_69f621d139f081909f9ca04e04095dba completed May 2, 2026, 4:09 p.m.
PD Predicate disambiguation batch_69f61b3ee7b08190a0a1bc5d26b757aa completed May 2, 2026, 3:41 p.m.
Created at: April 27, 2026, 7 a.m.