Triple
T21936013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fubuki class |
E541689
|
entity |
| Predicate | shipTypeGeneration |
P65451
|
FINISHED |
| Object | first generation Special Type destroyer |
—
|
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: first generation Special Type destroyer | Statement: [Fubuki class, shipTypeGeneration, first generation Special Type destroyer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shipTypeGeneration Context triple: [Fubuki class, shipTypeGeneration, first generation Special Type destroyer]
-
A.
shipTypeProduced
Indicates that a particular type of ship is produced, built, or manufactured by a given entity.
-
B.
navalClassGeneration
chosen
Indicates that one naval class belongs to a particular generational sequence or iteration relative to another naval class.
-
C.
shipClass
Indicates the classification or type category to which a particular ship belongs.
-
D.
craftType
Indicates the specific kind or category of craft or vessel associated with an entity.
-
E.
launchVehicleGeneration
Indicates the generational version or iteration of a launch vehicle within a family of related launch systems.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f124048fe48190987340d5a6945176 |
completed | April 28, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:53 p.m.