Triple
T35804154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 金鯱 |
E1035061
|
entity |
| Predicate | 関連する信仰 |
P102165
|
FINISHED |
| Object | 水を司る霊獣としての鯱信仰 |
—
|
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: 水を司る霊獣としての鯱信仰 | Statement: [金鯱, 関連する信仰, 水を司る霊獣としての鯱信仰]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 関連する信仰 Context triple: [金鯱, 関連する信仰, 水を司る霊獣としての鯱信仰]
-
A.
associatedReligionOrBelief
chosen
Indicates that an entity is connected to, identified with, or characterized by a particular religion or belief system.
-
B.
religiousObjectAssociated
Indicates that a religious object is associated with, connected to, or used in relation to another entity (such as a person, place, event, or practice).
-
C.
associatedReligionText
Indicates that there is a textual work (such as a scripture or religious document) that is specifically associated with, or pertains to, a given religion.
-
D.
relatedBelief
Indicates that one belief is connected to, derived from, or otherwise associated with another belief in some meaningful way.
-
E.
hasReligious
Indicates that an entity is associated with, practices, or adheres to a particular religion or religious affiliation.
- 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_69f76e169bd081909f16cd8c9ee7870c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a283388c81908e4a9ee3369e8d6f |
completed | May 3, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.