Triple
T33412248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uber Diamond |
E855617
|
entity |
| Predicate | programRelationship |
P84787
|
FINISHED |
| Object | tier within Uber Rewards hierarchy |
—
|
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: tier within Uber Rewards hierarchy | Statement: [Uber Diamond, programRelationship, tier within Uber Rewards hierarchy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programRelationship Context triple: [Uber Diamond, programRelationship, tier within Uber Rewards hierarchy]
-
A.
reportsRelationship
Indicates that one entity formally provides information, findings, or status about another entity or situation.
-
B.
seriesRelation
Indicates a relationship where one entity is part of, follows from, or is otherwise connected to another within an ordered series or sequence.
-
C.
playerRelations
Indicates the nature or status of the relationship between players, such as alliances, rivalries, or other interpersonal dynamics.
-
D.
subjectRelation
chosen
Indicates that one entity stands in a specified relational role or connection to another entity.
-
E.
unitRelation
Indicates a relationship between units, such as how one unit is associated with, derived from, or converted to another.
- 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_69f3496f04a08190804e56ac5098b8e4 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f74c70fd248190a9d5543afcb08211 |
completed | May 3, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69f7478e3b548190a51d5d436e2bb036 |
completed | May 3, 2026, 1:03 p.m. |
Created at: May 1, 2026, 1:36 a.m.