Triple
T29846474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 三光作戦 |
E757940
|
entity |
| Predicate | 加害者 |
P103759
|
FINISHED |
| Object | 日本軍兵士 |
—
|
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: 日本軍兵士 | Statement: [三光作戦, 加害者, 日本軍兵士]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 加害者 Context triple: [三光作戦, 加害者, 日本軍兵士]
-
A.
perpetratorType
chosen
Indicates the classification or category of the entity that carried out or is responsible for a harmful, illegal, or otherwise wrongful act.
-
B.
suspectedPerpetrator
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
C.
perpetratorDescription
Indicates that the subject provides a textual description or characterization of the perpetrator involved in an act or incident.
-
D.
perpetratorStatus
Indicates the role or condition of an individual in relation to committing or being responsible for a specific harmful or criminal act.
-
E.
perpetratorAlias
Indicates that an entity is known or referred to by an alternative name or alias specifically in the context of being the perpetrator of an act or offense.
- 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_69f2245a82cc8190a387e7d0118d710b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f676438624819086aabd1b6e5fef4c |
completed | May 2, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:42 p.m.