Triple
T14048006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oyashio-class submarine |
E338009
|
entity |
| Predicate | firstCommissioned |
P112615
|
FINISHED |
| Object | late 1990s |
—
|
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: late 1990s | Statement: [Oyashio-class submarine, firstCommissioned, late 1990s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstCommissioned Context triple: [Oyashio-class submarine, firstCommissioned, late 1990s]
-
A.
commissionedInService
Indicates that an entity was formally brought into active service or duty within a particular organization, role, or context.
-
B.
commissionedFirstUnit
Indicates that one entity formally brought the first operational unit of another entity into active service or use.
-
C.
firstGeneratorCommissioned
Indicates that the first generator in a system or facility has been officially put into operation or brought online.
-
D.
commissionedYear
Indicates the year in which something (typically a work, project, or item) was formally ordered, authorized, or put into production.
-
E.
firstReactorCommissioned
Indicates that the first reactor in a given context has been officially brought into operation or commissioned.
- F. None of above. chosen
Provenance (4 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de3c88b5e48190b0f0149102c08992 |
completed | April 14, 2026, 1:09 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
| PDg | Predicate description generation | batch_69de2398856c81908bed6070e4ca6ab1 |
completed | April 14, 2026, 11:23 a.m. |
Created at: April 9, 2026, 10:20 p.m.