Triple
T22440214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 仙洞御所（退位後） |
E554733
|
entity |
| Predicate | 所在国の元首制度 |
P115919
|
FINISHED |
| Object | 日本の象徴天皇制 |
—
|
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: 日本の象徴天皇制 | Statement: [仙洞御所（退位後）, 所在国の元首制度, 日本の象徴天皇制]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所在国の元首制度 Context triple: [仙洞御所（退位後）, 所在国の元首制度, 日本の象徴天皇制]
-
A.
headOfStateSystem
chosen
Indicates the type or structure of the system by which a state's head of state is selected, organized, or constituted.
-
B.
headOfStateIsAlsoHeadOfGovernment
Indicates that the same individual holds both the role of head of state and the role of head of government.
-
C.
headOfGovernmentSystem
Indicates the system or structure by which the head of government is selected, organized, and empowered within a political entity.
-
D.
typeOfGovernmentHead
Indicates the specific role or office that serves as the head of a given system of government.
-
E.
headOfGovernmentTypically
Indicates that one entity is the person who usually serves as the head of government for the other entity (such as a country, state, or jurisdiction).
- 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_69e11e5010e48190ae1e9c9db9697637 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ae0edcc8190919b198035de0df2 |
completed | April 29, 2026, 1:12 a.m. |
| PD | Predicate disambiguation | batch_69e898a327948190beee5e168006a0a7 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.