Triple
T10524386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SAS EuroBonus Diamond |
E248258
|
entity |
| Predicate | cardDesign |
P90360
|
FINISHED |
| Object | typically dark or black-themed elite card design |
—
|
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: typically dark or black-themed elite card design | Statement: [SAS EuroBonus Diamond, cardDesign, typically dark or black-themed elite card design]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cardDesign Context triple: [SAS EuroBonus Diamond, cardDesign, typically dark or black-themed elite card design]
-
A.
cardColor
chosen
Indicates the color attribute assigned to a card in the relationship.
-
B.
cardFormat
Indicates the specific layout or structural style in which a card or card-like item is presented or encoded.
-
C.
cardType
Indicates the classification or category assigned to a card within a given system or context.
-
D.
cardFamily
Indicates that one card belongs to the same family, series, or closely related group as another card.
-
E.
cardSize
Indicates the specific dimensions or format assigned to a card within a given context or system.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509f4020c8190b78c49da086df757 |
completed | April 7, 2026, 1:43 p.m. |
| PD | Predicate disambiguation | batch_69d4fb94fa10819091f585bab4379c6f |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:29 p.m.