Triple
T22324439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 第二次上海事変 |
E551866
|
entity |
| Predicate | 発端となった事件 |
P48572
|
FINISHED |
| Object | 大山事件 |
—
|
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: 大山事件 | Statement: [第二次上海事変, 発端となった事件, 大山事件]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 発端となった事件 Context triple: [第二次上海事変, 発端となった事件, 大山事件]
-
A.
関連事件
Indicates a relationship where one event is connected or related to another event, typically as part of the same case, incident, or context.
-
B.
allegedStartEvent
chosen
Indicates that an entity is claimed or reported (but not confirmed) to be the starting point or initiation of a particular event or process.
-
C.
incidentName
Indicates the specific name or label assigned to an incident within a system or context.
-
D.
isMajorEventOf
Indicates that an event is a primary, significant, or defining occurrence within the context of another entity (such as a project, period, or process).
-
E.
began
Indicates that one entity initiated or started an action, event, or state involving another entity or context.
- 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15767425481909547bfe294fe06de |
completed | April 29, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e73004d9e88190bb862319a5aea06b |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:42 p.m.