Triple
T18132607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virgin Atlantic Clubhouse |
E434050
|
entity |
| Predicate | cateringStyle |
P14779
|
FINISHED |
| Object | à la carte restaurant‑style dining |
—
|
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: à la carte restaurant‑style dining | Statement: [Virgin Atlantic Clubhouse, cateringStyle, à la carte restaurant‑style dining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cateringStyle Context triple: [Virgin Atlantic Clubhouse, cateringStyle, à la carte restaurant‑style dining]
-
A.
diningStyle
Indicates the manner or format in which dining is conducted, such as casual, formal, buffet, or family-style.
-
B.
cateringIncludes
Indicates that a catering service or arrangement encompasses or provides the specified item, service, or component as part of its offering.
-
C.
servingStyle
chosen
Indicates how something (typically food or drink) is presented or offered for consumption or use.
-
D.
feastType
Indicates the specific kind or category of feast associated with an event or occasion.
-
E.
foodPreparationStyle
Indicates the manner or method by which food is prepared, cooked, or processed.
- 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_69d8b909e8cc81908df4cc2b8ea6d11f |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddf2c68881909dfbe59df15ddccc |
completed | April 19, 2026, 1:51 p.m. |
| PD | Predicate disambiguation | batch_69e43317d11c81908d1dc14921566b47 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:29 a.m.