Triple
T13024489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamigamo Shrine |
E326264
|
entity |
| Predicate | guardianDeityType |
P9989
|
FINISHED |
| Object | thunder deity |
—
|
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: thunder deity | Statement: [Kamigamo Shrine, guardianDeityType, thunder deity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardianDeityType Context triple: [Kamigamo Shrine, guardianDeityType, thunder deity]
-
A.
typeOfDeity
chosen
Indicates that one entity is classified as a specific kind or category of deity in relation to another.
-
B.
hasGuardianDeity
Indicates that an entity is under the protection or patronage of a specific guardian deity.
-
C.
deityCategory
Indicates that one entity is classified as belonging to a particular category or type of deity in relation to another entity.
-
D.
attributeOfDeity
Indicates that something is a characteristic, quality, or property belonging to a deity.
-
E.
patronDeityOf
Indicates that one entity serves as the protective or primary deity associated with, worshipped by, or presiding over another entity (such as a person, group, or place).
- 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_69d8076cc45c81908123123f43e69266 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97efac71881908a21d70c3c6ce099 |
completed | April 10, 2026, 10:51 p.m. |
| PD | Predicate disambiguation | batch_69d97dc39a0881908119c62e31bf6182 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 8:52 p.m.