Triple
T26665732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sichuan Airlines |
E672180
|
entity |
| Predicate | aircraftManufacturerPreference |
P53350
|
FINISHED |
| Object | Airbus |
—
|
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: Airbus | Statement: [Sichuan Airlines, aircraftManufacturerPreference, Airbus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftManufacturerPreference Context triple: [Sichuan Airlines, aircraftManufacturerPreference, Airbus]
-
A.
operatesAircraftBrand
chosen
Indicates that an entity actively uses or runs aircraft belonging to a specified brand in its operations.
-
B.
appliedToAircraftBuiltBy
Indicates that something (such as a regulation, modification, or action) is applied specifically to aircraft that were built by a particular manufacturer or builder.
-
C.
aircraftManufacturerOfAircraft
Indicates that a given manufacturer is the producer or builder of a specified aircraft.
-
D.
aircraftMostAssociatedWith
Indicates the aircraft that is most strongly or commonly linked to, used by, or representative of a given entity compared to other aircraft.
-
E.
intendedAircraftManufacturer
Indicates that one entity is the manufacturer for which an aircraft (or aircraft model) is designed or planned, rather than necessarily the one that ultimately builds it.
- 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_69eecda00a9c8190b2691f4d89db03b6 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6247480cc8190a887eedaeb94615c |
completed | May 2, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69f623a7539c8190b71797f583da9f63 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 3:09 a.m.