Triple
T51698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constitution of Japan |
E1013
|
entity |
| Predicate | enshrines |
P2950
|
FINISHED |
| Object | civilian control of the military |
—
|
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: civilian control of the military | Statement: [Constitution of Japan, enshrines, civilian control of the military]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enshrines Context triple: [Constitution of Japan, enshrines, civilian control of the military]
-
A.
worshippedIn
Indicates that a particular deity, figure, or object of reverence is the focus of religious or spiritual worship within a specified place or context.
-
B.
hasReligiousSite
Indicates that a location or entity possesses, contains, or is associated with a religious site such as a temple, church, mosque, shrine, or similar place of worship.
-
C.
hasPlaceOfWorship
Indicates that an entity possesses, contains, or is associated with a designated location used for religious or spiritual worship.
-
D.
resurrectionPlace
Indicates the location where an entity is brought back to life or restored from death.
-
E.
religiousFunction
Indicates that one entity serves a religious role, purpose, or function in relation to another entity.
- F. None of above. chosen
Provenance (4 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24ba7016481909d595402712db6e2 |
completed | Feb. 28, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69a24ac23f04819080cef9365ed990d4 |
completed | Feb. 28, 2026, 1:54 a.m. |
| PDg | Predicate description generation | batch_69a24ba5da048190a484963cb5a9bb2b |
completed | Feb. 28, 2026, 1:57 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.