Triple
T2229985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Airways |
E48741
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object |
Air Chefs
Air Chefs is an airline catering company that provides in-flight meals and related services, primarily supporting South African Airways and other carriers.
|
E245440
|
NE FINISHED |
How this triple was built (4 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: Air Chefs | Statement: [South African Airways, hasSubsidiary, Air Chefs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Air Chefs Context triple: [South African Airways, hasSubsidiary, Air Chefs]
-
A.
Pilots
The Pilots are the athletic teams representing the University of Portland in NCAA Division I sports.
-
B.
Chefs de France
Chefs de France is a popular table-service French restaurant located in the France Pavilion at EPCOT in Walt Disney World Resort.
-
C.
Cook
Cook is a surname shared by various notable individuals, including members of singer-songwriter Alicia Keys' family.
-
D.
Charlie the cook
Charlie the cook is a supporting character in the 1933 adventure film "Son of Kong," serving as the ship’s cook and providing comic relief during the expedition.
-
E.
Wingo
Wingo is a Colombian low-cost airline operating domestic and international flights across Latin America and the Caribbean.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Air Chefs Triple: [South African Airways, hasSubsidiary, Air Chefs]
Generated description
Air Chefs is an airline catering company that provides in-flight meals and related services, primarily supporting South African Airways and other carriers.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Air Chefs Target entity description: Air Chefs is an airline catering company that provides in-flight meals and related services, primarily supporting South African Airways and other carriers.
-
A.
Pilots
The Pilots are the athletic teams representing the University of Portland in NCAA Division I sports.
-
B.
Chefs de France
Chefs de France is a popular table-service French restaurant located in the France Pavilion at EPCOT in Walt Disney World Resort.
-
C.
Cook
Cook is a surname shared by various notable individuals, including members of singer-songwriter Alicia Keys' family.
-
D.
Charlie the cook
Charlie the cook is a supporting character in the 1933 adventure film "Son of Kong," serving as the ship’s cook and providing comic relief during the expedition.
-
E.
Wingo
Wingo is a Colombian low-cost airline operating domestic and international flights across Latin America and the Caribbean.
- F. None of above. chosen
Provenance (5 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_69a88aa51b388190949868ec9766e587 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc069e0ac8190bcda8cba9f5c7a5d |
completed | March 7, 2026, 6:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae656a1f788190a08c3283bfedb6f4 |
completed | March 9, 2026, 6:15 a.m. |
| NEDg | Description generation | batch_69ae65d4f26481909808c97b95ca9b30 |
completed | March 9, 2026, 6:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae6670b6d88190a09023fae63f4000 |
completed | March 9, 2026, 6:19 a.m. |
Created at: March 4, 2026, 7:47 p.m.