Triple
T33941263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Takakura |
E870169
|
entity |
| Predicate | eraTransitionAfterReign |
P106462
|
FINISHED |
| Object | toward early Kamakura period power structure |
—
|
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: toward early Kamakura period power structure | Statement: [Emperor Takakura, eraTransitionAfterReign, toward early Kamakura period power structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eraTransitionAfterReign Context triple: [Emperor Takakura, eraTransitionAfterReign, toward early Kamakura period power structure]
-
A.
appliesAfterReignOf
chosen
Indicates that something becomes relevant, valid, or in effect only after the reign or rule of a specified entity has ended.
-
B.
endOfReign
Indicates the point in time or event at which a ruler’s or leader’s period of authority or reign concludes.
-
C.
endOfSecondReign
Indicates that a second period of rule or governance by an entity has concluded.
-
D.
afterAbdication
Indicates that one event, state, or action occurs subsequent to the abdication of a person from a position of authority or office.
-
E.
successorDynastyBecame
Indicates that one dynasty replaced another and formally became its successor.
- 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.