Triple
T394123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Courts of Japan |
E8942
|
entity |
| Predicate | canUphold |
P12547
|
FINISHED |
| Object | judgments of lower courts |
—
|
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: judgments of lower courts | Statement: [High Courts of Japan, canUphold, judgments of lower courts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canUphold Context triple: [High Courts of Japan, canUphold, judgments of lower courts]
-
A.
supportsAccountType
Indicates that one entity is compatible with, or able to operate for, a specified type or category of account.
-
B.
canMandate
Indicates that one entity has the authority or power to require another entity to perform or comply with something.
-
C.
authorizesFundingFor
Indicates that one entity grants official approval or permission for financial resources to be provided to another entity or purpose.
-
D.
supportsAddressTypes
Indicates that an entity is capable of handling or working with one or more specified types of addresses.
-
E.
canUse
Indicates that one entity has the ability, permission, or suitability to make use of another entity or resource.
- 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_69a2e7f55c60819097aff65ea2ca2832 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec77a8a08190b6f96373aa8c1346 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e96bd3848190a66ca14dfbd26da5 |
completed | Feb. 28, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69a2ea7d03a88190aab72e61d8673488 |
completed | Feb. 28, 2026, 1:15 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.