Triple
T22139842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 犬養毅 |
E547127
|
entity |
| Predicate | 通算在任期間 |
P540
|
FINISHED |
| Object | 約5か月 |
—
|
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: 約5か月 | Statement: [犬養毅, 通算在任期間, 約5か月]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 通算在任期間 Context triple: [犬養毅, 通算在任期間, 約5か月]
-
A.
termInOffice
Indicates the period during which an individual officially holds a particular office or position.
-
B.
termInOfficeContext
Indicates that one entity’s tenure or period of holding an office, role, or position is being specified or contextualized in relation to another entity or timeframe.
-
C.
hasTimePeriodOfService
Indicates that an entity is associated with a specific span of time during which it provided service or was actively serving.
-
D.
numberOfTermInOffice
Indicates the specific ordinal count of how many terms an entity has served in a particular office or position.
-
E.
termLength
chosen
Indicates the duration or period of time for which an agreement, position, or condition remains in effect.
- 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_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129bda1208190b851ae5c68b760e9 |
completed | April 28, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69e71b384e008190b723c9a0f1089d66 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:32 p.m.