Triple
T31224086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cavour-class aircraft carrier |
E796089
|
entity |
| Predicate | airWingSizeApproximate |
P90293
|
FINISHED |
| Object | up to 20–25 aircraft |
—
|
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: up to 20–25 aircraft | Statement: [Cavour-class aircraft carrier, airWingSizeApproximate, up to 20–25 aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airWingSizeApproximate Context triple: [Cavour-class aircraft carrier, airWingSizeApproximate, up to 20–25 aircraft]
-
A.
airWingType
Indicates the classification or category of an air wing associated with an entity.
-
B.
airWingCapacity
chosen
Indicates the maximum number or volume of aircraft or air operations that an air wing can support or handle.
-
C.
wingSpanVariant
Indicates a relationship where one wing span measurement is a variant or alternative form of another wing span measurement.
-
D.
wingArea
Indicates the total surface area covered by an entity’s wing or wings.
-
E.
wingLength
Indicates the length or measurement of a wing associated with an entity.
- 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_69f224da98f88190ab32f690cce5d303 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69c5030b88190bac4667e104238af |
completed | May 3, 2026, 12:52 a.m. |
| PD | Predicate disambiguation | batch_69f696673214819094350e1d2648ef34 |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 29, 2026, 9:10 p.m.