Triple
T18567816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 軍教育総監 |
E453799
|
entity |
| Predicate | 管轄分野 |
P69378
|
FINISHED |
| Object | 軍事教育 |
—
|
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: 軍事教育 | Statement: [軍教育総監, 管轄分野, 軍事教育]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 管轄分野 Context triple: [軍教育総監, 管轄分野, 軍事教育]
-
A.
fieldDivision
Indicates a relationship where a larger field or area is partitioned into smaller sections or subdivisions.
-
B.
hasFieldDivision
Indicates that one entity is organizationally divided into, or associated with, a specific field-based subdivision of another entity.
-
C.
divisionFocus
Indicates a relationship where attention, resources, or activity are specifically directed toward a particular division within a larger organization or structure.
-
D.
managementJurisdiction
chosen
Indicates that one entity has formal authority or responsibility to manage, oversee, or administer another entity or domain within a defined scope or area.
-
E.
governanceArea
Indicates the geographic or jurisdictional area over which an entity has governing authority or responsibility.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53affc3e08190b4d16b5ccb0bddbc |
completed | April 19, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69e478c16e0c8190b03966aa23c395a6 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:43 a.m.