Triple
T29215200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 柿本人麻呂 |
E740648
|
entity |
| Predicate | 宮廷との関係 |
P57456
|
FINISHED |
| Object | 朝廷に仕えた宮廷歌人 |
—
|
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: 朝廷に仕えた宮廷歌人 | Statement: [柿本人麻呂, 宮廷との関係, 朝廷に仕えた宮廷歌人]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 宮廷との関係 Context triple: [柿本人麻呂, 宮廷との関係, 朝廷に仕えた宮廷歌人]
-
A.
associatedWithPalace
chosen
Indicates a relationship where an entity has a connection, link, or involvement with a palace, such as through location, function, ownership, or affiliation.
-
B.
国の元首との関係
Indicates a relationship or connection that an entity has with the head of state of a country.
-
C.
皇位継承順位への関係
Indicates the relationship of an entity to the line of succession to the imperial throne, such as its position, eligibility, or connection within that succession order.
-
D.
hasRoyalHousehold
Indicates that an entity possesses or is associated with a specific royal household as its official domestic or courtly establishment.
-
E.
associatedWithEmperor
Indicates a relationship in which an entity has a connection, link, or affiliation with an emperor, such as through service, influence, kinship, or shared authority.
- 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_69f07cba2f808190a2746477d4e8345b |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f66408d068819082a94491d663bff2 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 12:13 p.m.