Triple
T27602587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | submarine tender Takasaki |
E700089
|
entity |
| Predicate | shipTypeAfterConversion |
P21289
|
FINISHED |
| Object | light aircraft carrier |
—
|
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: light aircraft carrier | Statement: [submarine tender Takasaki, shipTypeAfterConversion, light aircraft carrier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shipTypeAfterConversion Context triple: [submarine tender Takasaki, shipTypeAfterConversion, light aircraft carrier]
-
A.
conversionOfShip
chosen
Indicates the process by which a ship is altered or transformed from one configuration, role, or specification into another.
-
B.
hullTypeConvertedFrom
Indicates that one hull type has been changed or transformed from another original hull type.
-
C.
originalShipType
Indicates the type or category of ship that an entity was originally classified or built as.
-
D.
shipTypeProduced
Indicates that a particular type of ship is produced, built, or manufactured by a given entity.
-
E.
naveType
Indicates the architectural or structural type or style of a building’s nave in relation to that nave.
- 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_69ef6a4e2e208190b63b7268f405785c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f63097501081909d2b6b969f9a4e2b |
completed | May 2, 2026, 5:12 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:08 p.m.