Triple
T14326638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 枝野幸男 |
E355231
|
entity |
| Predicate | 立憲民主党の創設者 |
P102368
|
FINISHED |
| Object | はい |
—
|
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: はい | Statement: [枝野幸男, 立憲民主党の創設者, はい]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 立憲民主党の創設者 Context triple: [枝野幸男, 立憲民主党の創設者, はい]
-
A.
foundingLeaderOf
chosen
Indicates that an entity is the primary founder who established and initially led another entity, such as an organization, movement, or institution.
-
B.
founderKnownFor
Indicates that a founder is particularly recognized or notable for a specific work, achievement, product, or contribution.
-
C.
commissionerAtFounding
Indicates that an entity served as a commissioner at the time of an organization's or institution's founding.
-
D.
presidentOfSenateCofounder
Indicates that an individual both serves as president of a senate and is a cofounder of the associated organization or institution.
-
E.
notablePrimeMinisterFromParty
Indicates that the subject is a prime minister who is notably associated with, or recognized as coming from, the specified political party.
- 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_69d8278fa2108190bc0d0e7939c1eb03 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de883e6a288190b6c22f630a1eef3c |
completed | April 14, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69de2a9515f4819081aabf251bca5878 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:13 a.m.