Triple
T33977462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nakajima Ki-34 |
E871179
|
entity |
| Predicate | civilianDerivativeOf |
P58433
|
FINISHED |
| Object | Nakajima AT-2 |
—
|
NE NERFINISHED |
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: Nakajima AT-2 | Statement: [Nakajima Ki-34, civilianDerivativeOf, Nakajima AT-2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: civilianDerivativeOf Context triple: [Nakajima Ki-34, civilianDerivativeOf, Nakajima AT-2]
-
A.
civilianVariant
chosen
Indicates that one entity is a civilian version or non-military counterpart of another entity.
-
B.
civilian
Indicates that an entity is a non-military person or object associated with civilian status or context.
-
C.
civilianUse
Indicates that something is intended for, suitable for, or actually used by civilians rather than military or combat purposes.
-
D.
isCivilMilitary
Indicates that an entity or relationship involves both civilian and military components or functions.
-
E.
civilOrMilitary
Indicates that something is classified as either civil (non-military) or military in nature or function.
- 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_69f3499da0188190ab1a4ff06fb06a2a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.