Triple
T19475924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese occupation of Attu |
E487245
|
entity |
| Predicate | civilianOutcome |
P1405
|
FINISHED |
| Object | deportation of Aleut inhabitants to Japan |
—
|
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: deportation of Aleut inhabitants to Japan | Statement: [Japanese occupation of Attu, civilianOutcome, deportation of Aleut inhabitants to Japan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: civilianOutcome Context triple: [Japanese occupation of Attu, civilianOutcome, deportation of Aleut inhabitants to Japan]
-
A.
civilian
Indicates that an entity is a non-military person or object associated with civilian status or context.
-
B.
civilianImpact
chosen
Indicates the extent to which an action, event, or situation affects civilians, especially in terms of harm, disruption, or other consequences.
-
C.
civilianResponse
Indicates how civilians react or respond to a particular event, action, or situation.
-
D.
civilianTarget
Indicates that the action or operation is directed at, affects, or designates civilians or civilian objects as the target.
-
E.
civilianUse
Indicates that something is intended for, suitable for, or actually used by civilians rather than military or combat purposes.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633f1f8688190a2df574a9e0a194d |
completed | April 20, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7883308190b73912a71a35a835 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:39 p.m.