Triple
T26136614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GrabRewards |
E659398
|
entity |
| Predicate | tierDeterminedBy |
P159984
|
FINISHED |
| Object | points earned in a qualification period |
—
|
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: points earned in a qualification period | Statement: [GrabRewards, tierDeterminedBy, points earned in a qualification period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tierDeterminedBy Context triple: [GrabRewards, tierDeterminedBy, points earned in a qualification period]
-
A.
tierType
Indicates the classification level or rank assigned to an entity within a multi-level or hierarchical system.
-
B.
rankTier
Indicates the classification level or tier assigned to an entity within a ranking or hierarchical system.
-
C.
tierInNorthAmericanSystem
Indicates that an entity occupies a specified competitive or organizational level within the North American system for that domain (e.g., sports leagues, education, or other structured hierarchies).
-
D.
priorityDeterminedBy
Indicates that the priority or importance level of one entity is established based on another entity or set of factors.
-
E.
tiered
Indicates that something is organized into multiple hierarchical levels or layers, often with differing degrees of priority, access, or benefit.
- F. None of above. chosen
Provenance (4 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_69ee5bc3c20c8190bf2cf272f4170e95 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60b97942c8190b3d913dcdcd30e08 |
completed | May 2, 2026, 2:35 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
| PDg | Predicate description generation | batch_69f5f6b32a8881909baa0db57b80d56a |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 26, 2026, 8:18 p.m.