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.