Triple
T22533737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 岸信介 |
E557105
|
entity |
| Predicate | 政治的特徴 |
P5316
|
FINISHED |
| Object | 対米協調路線 |
—
|
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: 対米協調路線 | Statement: [岸信介, 政治的特徴, 対米協調路線]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 政治的特徴 Context triple: [岸信介, 政治的特徴, 対米協調路線]
-
A.
hasPoliticalCharacteristic
chosen
Indicates that an entity possesses a specific political attribute, quality, or affiliation.
-
B.
politicalPeculiarity
Indicates a distinctive or unusual political characteristic, condition, or feature that sets a political entity or situation apart from typical norms.
-
C.
politicalForm
Indicates the type or structure of governance or political organization that characterizes an entity.
-
D.
mainPoliticalDevelopment
Indicates the primary or most significant political change, event, or evolution affecting an entity within a given period or context.
-
E.
featuresReversedPoliticsFrom
Indicates that one entity presents or embodies political views or alignments that are the opposite or inverse of those associated with another entity.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed952f48190b63225e7de131679 |
completed | April 29, 2026, 1:28 a.m. |
| PD | Predicate disambiguation | batch_69e898c864148190a3f5feec7967d49c |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:51 p.m.