Triple
T17473238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujiwara no Michikane |
E425471
|
entity |
| Predicate | regencyType |
P112360
|
FINISHED |
| Object | kampaku |
—
|
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: kampaku | Statement: [Fujiwara no Michikane, regencyType, kampaku]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regencyType Context triple: [Fujiwara no Michikane, regencyType, kampaku]
-
A.
regency
Indicates that one entity exercises ruling authority on behalf of another, typically when the latter is unable to govern directly (such as due to minority, absence, or incapacity).
-
B.
hasRegencyType
chosen
Indicates that an entity is associated with a specific type or form of regency (i.e., a particular kind of regent rule or regent arrangement).
-
C.
hasRegency
Indicates that one entity exercises regency authority or governing power on behalf of another, typically during the latter’s minority, incapacity, or absence.
-
D.
includesRegency
Indicates that one entity’s scope, period, or authority encompasses or contains a regency associated with another entity.
-
E.
regentStyle
Indicates the manner, fashion, or stylistic approach in which a regent exercises authority or performs their governing role.
- 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_69d889dbc2e88190b18ea6115e819258 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451b990848190b2e8510d67e94b79 |
completed | April 19, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f341c88190adabe526d8903b05 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:47 a.m.