Triple
T186470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nihon-koku Kenpō |
E3991
|
entity |
| Predicate | draftInfluencedBy |
P1994
|
FINISHED |
| Object | Allied Occupation authorities |
—
|
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: Allied Occupation authorities | Statement: [Nihon-koku Kenpō, draftInfluencedBy, Allied Occupation authorities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: draftInfluencedBy Context triple: [Nihon-koku Kenpō, draftInfluencedBy, Allied Occupation authorities]
-
A.
influencedWork
chosen
Indicates that one work has had a significant impact on the creation, style, content, or development of another work.
-
B.
influenced
Indicates that one entity has affected, shaped, or altered another entity’s state, behavior, or characteristics.
-
C.
draftedBy
Indicates that something (such as a document, plan, or version) was created or written in its initial form by a particular agent or author.
-
D.
draft
Indicates that one entity prepares an initial or preliminary version of something, typically a document, plan, or design, which may be revised later.
-
E.
wrote
Indicates that an entity is the author or creator of a written work involving another entity.
- 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_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. |
Created at: Feb. 28, 2026, 2:40 a.m.