Triple
T36923963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virgin Group airlines |
E913284
|
entity |
| Predicate | usesBrandingTheme |
P183611
|
FINISHED |
| Object | red and white livery |
—
|
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: red and white livery | Statement: [Virgin Group airlines, usesBrandingTheme, red and white livery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesBrandingTheme Context triple: [Virgin Group airlines, usesBrandingTheme, red and white livery]
-
A.
usesBrandingScheme
chosen
Indicates that one entity applies or follows the specific branding scheme defined or provided by another entity.
-
B.
hasBranding
Indicates that one entity carries, displays, or is associated with the brand identity of another entity.
-
C.
usesThemeBy
Indicates that one entity incorporates, applies, or is based on a theme that was created, defined, or provided by another entity.
-
D.
usesThemeFrom
Indicates that one work incorporates, references, or is based on the thematic material of another work.
-
E.
supportsThemeOf
Indicates that one entity reinforces, aligns with, or contributes to the central theme expressed by 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fdcee55c8190ac5c514365310457 |
completed | May 5, 2026, 2:25 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.