Triple
T4910202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kasuga Taisha |
E110211
|
entity |
| Predicate | enshrinesKami |
P2950
|
FINISHED |
| Object | four principal deities |
—
|
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: four principal deities | Statement: [Kasuga Taisha, enshrinesKami, four principal deities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enshrinesKami Context triple: [Kasuga Taisha, enshrinesKami, four principal deities]
-
A.
enshrines
chosen
Indicates that one entity formally preserves, protects, or honors another by giving it a permanent, often sacred or legally recognized, status.
-
B.
numberOfShrines
Indicates the total count of shrines associated with a given entity or context.
-
C.
hasShrinesIn
Indicates that one entity possesses or maintains shrines that are located within the area or domain of another entity.
-
D.
associatedShrine
Indicates that there is a specific shrine linked or connected to the given entity, typically as its dedicated or related place of worship or reverence.
-
E.
typicalShrineFeature
Indicates that something is a characteristic or commonly found element of a shrine.
- 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_69bd44132b94819088522d92beaadc78 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e99414081908c3d3283f563bba4 |
completed | March 20, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69bd6c325e188190823836d79934e9bc |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:29 p.m.