Triple
T7312647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Air SKYPASS Morning Calm Premium |
E168130
|
entity |
| Predicate | statusLevelRelativeToSKYPASSBase |
P28991
|
FINISHED |
| Object | higher |
—
|
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: higher | Statement: [Korean Air SKYPASS Morning Calm Premium, statusLevelRelativeToSKYPASSBase, higher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusLevelRelativeToSKYPASSBase Context triple: [Korean Air SKYPASS Morning Calm Premium, statusLevelRelativeToSKYPASSBase, higher]
-
A.
sponsorLevel
Indicates the degree or tier of sponsorship that one entity provides to another.
-
B.
statusLevelAbove
chosen
Indicates that one entity’s status level is higher or more advanced than another entity’s status level.
-
C.
comfortLevelRelativeToEconomy
Indicates the degree of comfort or quality relative to a standard economic or budget level.
-
D.
membershipLevelAbove
Indicates that one entity’s membership level is ranked higher or more privileged than another entity’s membership level.
-
E.
affiliateLevelOf
Indicates the hierarchical rank or tier of an entity within an affiliate or partnership program.
- 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_69c6888d8e3c81909db79714903baf31 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6ec02319c819096d25e3683943886 |
completed | March 27, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_69c6e7705f4881909793071dee50c557 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:02 p.m.