Triple
T186492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nihon-koku Kenpō |
E3991
|
entity |
| Predicate | amendmentProcedureDefinedIn |
P6722
|
FINISHED |
| Object | Article 96 |
—
|
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: Article 96 | Statement: [Nihon-koku Kenpō, amendmentProcedureDefinedIn, Article 96]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: amendmentProcedureDefinedIn Context triple: [Nihon-koku Kenpō, amendmentProcedureDefinedIn, Article 96]
-
A.
laterConstitutionalAct
Indicates that one constitutional act occurs after another in time, establishing a later legal or constitutional measure relative to a prior one.
-
B.
constitutionalNumber
Indicates that an entity has a specific number or count defined or constrained by a constitution or foundational governing document.
-
C.
amendmentCount
Indicates the number of amendments that have been made to a given item, document, or entity.
-
D.
previousConstitutionRevised
Indicates that a prior constitution has been modified or updated through a formal revision process.
-
E.
effectOfAmendments
Indicates the causal impact or consequences that specific amendments have on something, such as a law, document, or situation.
- 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_69a25497e2f08190a040f8c6e1842643 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a2594809288190b3d3b1283e7e0d00 |
completed | Feb. 28, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69a25670feb081908e26a2543ebe7b3a |
completed | Feb. 28, 2026, 2:44 a.m. |
| PDg | Predicate description generation | batch_69a257e763d081908c54ad57d8d3060d |
completed | Feb. 28, 2026, 2:50 a.m. |
Created at: Feb. 28, 2026, 2:40 a.m.