Triple
T30988981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akron-class airship |
E789614
|
entity |
| Predicate | parasiteAircraftType |
P6548
|
FINISHED |
| Object | Curtiss F9C Sparrowhawk |
—
|
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: Curtiss F9C Sparrowhawk | Statement: [Akron-class airship, parasiteAircraftType, Curtiss F9C Sparrowhawk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parasiteAircraftType Context triple: [Akron-class airship, parasiteAircraftType, Curtiss F9C Sparrowhawk]
-
A.
aircraftType
Indicates the specific model or category of aircraft associated with an entity or event.
-
B.
poweredAircraftType
Indicates that one entity is a type or category of aircraft that is propelled by an onboard power source (e.g., engines), as opposed to being unpowered.
-
C.
intendedAircraft
Indicates that an aircraft is the one planned or designated to be used for a particular flight, mission, or operation.
-
D.
aircraftTypesCarried
chosen
Indicates that one entity (typically a vessel, facility, or platform) carries or is capable of carrying specific types of aircraft as part of its operations or configuration.
-
E.
typeOfAviation
Indicates the specific category or kind of aviation to which an entity belongs (e.g., commercial, military, private).
- 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_69f224c550b081909ddfceb0c3d03bdd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69f690ef92308190903a54fc74233269 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:56 p.m.