Triple
T1564332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uber Black |
E33397
|
entity |
| Predicate | relativeTier |
P25304
|
FINISHED |
| Object | more premium than UberX |
—
|
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: more premium than UberX | Statement: [Uber Black, relativeTier, more premium than UberX]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeTier Context triple: [Uber Black, relativeTier, more premium than UberX]
-
A.
relativeLevel
chosen
Indicates a comparative relationship specifying how one entity’s level, degree, or intensity of some property stands relative to that of another entity.
-
B.
representedLevel
Indicates that one entity denotes or encodes the degree, intensity, or value (i.e., the level) of another entity or property.
-
C.
topTierRelation
Indicates a relationship in which one entity belongs to the highest or most elite level within a ranked or hierarchical set of entities.
-
D.
rankEquivalent
Indicates that two entities hold the same rank or hierarchical level within a given ordering or classification system.
-
E.
firstTier
Indicates that one entity occupies the highest or primary level, rank, or priority relative to others in a hierarchical structure.
- 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_69a885f11b048190935025a035302715 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90fccd4b48190a44012888a00af7f |
completed | March 5, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69a907b872f0819096b3df6ad502c63e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.