Triple
T27700668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS John F. Kennedy (CVN-79) |
E698418
|
entity |
| Predicate | airWingCompatibility |
P70100
|
FINISHED |
| Object | F-35C Lightning II |
—
|
NE NERFINISHED |
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: F-35C Lightning II | Statement: [USS John F. Kennedy (CVN-79), airWingCompatibility, F-35C Lightning II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airWingCompatibility Context triple: [USS John F. Kennedy (CVN-79), airWingCompatibility, F-35C Lightning II]
-
A.
airWingType
Indicates the classification or category of an air wing associated with an entity.
-
B.
airWingCapacity
Indicates the maximum number or volume of aircraft or air operations that an air wing can support or handle.
-
C.
hasWingIn
Indicates that an entity possesses a wing that is located in or contained within another specified entity or structure.
-
D.
hasWingConfiguration
Indicates how an entity’s wings are arranged, structured, or configured relative to its body or to each other.
-
E.
supportsAircraft
chosen
Indicates that one entity is capable of accommodating, carrying, or enabling the operation of an aircraft.
- 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_69ef590ea74081908f0cd7500d85fa27 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f635a29ff08190bfd246ccaf0ddb4e |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:56 p.m.