Triple
T34072957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | International Aero Engines |
E873822
|
entity |
| Predicate | roleOfPratt & Whitney |
P182871
|
FINISHED |
| Object | major shareholder |
—
|
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: major shareholder | Statement: [International Aero Engines, roleOfPratt & Whitney, major shareholder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfPratt & Whitney Context triple: [International Aero Engines, roleOfPratt & Whitney, major shareholder]
-
A.
aircraftEngineManufacturer
Indicates that one entity is the manufacturer of the aircraft engine used by another entity.
-
B.
aircraftManufacturerPartner
Indicates a partnership relationship between an aircraft manufacturer and another entity, typically for collaboration in design, production, or related aerospace activities.
-
C.
aircraftManufacturerAtField
Indicates that an aircraft manufacturer operates or is located at a particular airfield or airport.
-
D.
wingManufacturer
Indicates that one entity is the manufacturer or producer of the wing component used by another entity.
-
E.
worksOnAircraft
Indicates that an entity performs work, maintenance, operation, or related tasks on an aircraft.
- F. None of above. chosen
Provenance (4 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_69f349a566808190a1c63b898f33cddf |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f794f24e588190965e39b77534d53f |
completed | May 3, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
| PDg | Predicate description generation | batch_69f791cad5e08190a8a04ca283dbecaa |
completed | May 3, 2026, 6:19 p.m. |
Created at: May 1, 2026, 1:52 a.m.