Triple
T34942986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 藍綬褒章 |
E1007775
|
entity |
| Predicate | conferralMonth |
P192090
|
FINISHED |
| Object | 春（4月・5月頃） |
—
|
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: 春（4月・5月頃） | Statement: [藍綬褒章, conferralMonth, 春（4月・5月頃）]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conferralMonth Context triple: [藍綬褒章, conferralMonth, 春（4月・5月頃）]
-
A.
conferredOn
Indicates that something (such as an honor, title, degree, or benefit) has been formally granted or bestowed upon a particular entity.
-
B.
culminationMonth
Indicates the month in which an event, process, or activity reaches its peak, completion, or final stage.
-
C.
proposedInMonth
Indicates that an entity (such as a proposal or plan) was formally proposed during a specific calendar month.
-
D.
conferralType
Indicates the specific manner or category in which something (such as a title, degree, or honor) is formally granted or conferred from one party to another.
-
E.
conferralBasis
Indicates the underlying reason, criterion, or justification on which something (such as a status, right, or benefit) is granted or conferred.
- 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_69f76dc513fc819084a1ff52abbfa5bc |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69fcf36bb86c8190a0a0ccf47cb56e5c |
completed | May 7, 2026, 8:17 p.m. |
Created at: May 3, 2026, 4 p.m.