Triple
T33319790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PlusPoints upgrade currency |
E853106
|
entity |
| Predicate | earnsAtTier |
P156482
|
FINISHED |
| Object | Premier Platinum |
—
|
NE NERFINISHED |
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: Premier Platinum | Statement: [PlusPoints upgrade currency, earnsAtTier, Premier Platinum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earnsAtTier Context triple: [PlusPoints upgrade currency, earnsAtTier, Premier Platinum]
-
A.
compensationTier
Indicates the level or category of compensation assigned to an entity relative to others.
-
B.
payGrade
Indicates the level or category of compensation assigned to an entity, typically reflecting its rank, role, or seniority in a pay structure.
-
C.
paidTierName
Indicates the specific name or label of the paid subscription tier associated with an entity.
-
D.
eliteTierSystem
Indicates a relationship where entities are organized or classified into higher, privileged levels within a tiered ranking or status system.
-
E.
offeredAtLevel
chosen
Indicates that something is provided, presented, or made available at a specific level, tier, or stage.
- 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_69f349685f088190b8fda44083a018a9 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:33 a.m.