Triple
T28062378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 339th Fighter Group, USAAF |
E709147
|
entity |
| Predicate | aircraftFeature |
P139485
|
FINISHED |
| Object | long-range drop tanks on P-51 Mustangs |
—
|
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: long-range drop tanks on P-51 Mustangs | Statement: [339th Fighter Group, USAAF, aircraftFeature, long-range drop tanks on P-51 Mustangs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftFeature Context triple: [339th Fighter Group, USAAF, aircraftFeature, long-range drop tanks on P-51 Mustangs]
-
A.
aircraftDesignFeature
Indicates a relationship where a specific design feature is associated with, or incorporated into, an aircraft.
-
B.
referredAircraftNotableFeature
Indicates that a referenced aircraft is associated with a notable or distinguishing feature.
-
C.
aircraftCapability
Indicates that an aircraft possesses a particular capability, function, or operational feature.
-
D.
flightDeckFeature
Indicates that one entity is a feature, component, or element that is part of or present on the flight deck of another entity.
-
E.
usesAircraftFeature
chosen
Indicates that one entity employs or takes advantage of a specific feature or capability 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_69ef9b6eb6d88190a3fea236eb0f7bed |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 27, 2026, 8:40 p.m.