Triple
T75067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akagi |
E1501
|
entity |
| Predicate | conversionType |
P631
|
FINISHED |
| Object | 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: aircraft carrier | Statement: [Akagi, conversionType, aircraft carrier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conversionType Context triple: [Akagi, conversionType, aircraft carrier]
-
A.
convertsTo
chosen
Indicates that one entity is transformed or changed into another entity, typically resulting in a different state, form, or representation.
-
B.
convertsFrom
Indicates that one entity is transformed or changed into another entity, with the source being the starting form or state.
-
C.
centralToDenomination
Indicates that something is a core or defining element within a particular religious denomination.
-
D.
adaptationType
Indicates the specific kind or category of adaptation that relates one entity to another or to a particular context.
-
E.
crossType
Indicates a relationship where one entity intersects, passes over, or traverses another, typically implying movement or extension across a boundary, area, or medium.
- 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_69a24c60d19c8190a1b6c105ca59ef5b |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a25314bd6c81908d1cfd4b83f20049 |
completed | Feb. 28, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_69a24eae77ec81909015906f31f2b62e |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.