Triple
T11989466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tupolev Tu-160 |
E285366
|
entity |
| Predicate | airRefueling |
P51382
|
FINISHED |
| Object | equipped with in-flight refueling probe |
—
|
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: equipped with in-flight refueling probe | Statement: [Tupolev Tu-160, airRefueling, equipped with in-flight refueling probe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airRefueling Context triple: [Tupolev Tu-160, airRefueling, equipped with in-flight refueling probe]
-
A.
airRefuellingMethod
Indicates the method or technique used to transfer fuel between aircraft during in-flight refuelling.
-
B.
airRefuellingBoom
Indicates that one entity provides or is equipped for in-flight refueling via a boom connection to another aircraft.
-
C.
aircraftTanker
Indicates that one aircraft is serving as an aerial refueling tanker for another aircraft.
-
D.
refuellingSystem
chosen
Indicates a system or mechanism used to supply fuel from one entity to another.
-
E.
hasRefuellingCapabilityFor
Indicates that one entity is capable of providing or performing refuelling operations for another 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903afe4388190a2cf2328e85adf9b |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d902abca70819098291aa51b593708 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:46 p.m.