Triple
T22213526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA luxury tax |
E549014
|
entity |
| Predicate | calculatedPer |
P71610
|
FINISHED |
| Object | dollar above tax threshold |
—
|
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: dollar above tax threshold | Statement: [NBA luxury tax, calculatedPer, dollar above tax threshold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: calculatedPer Context triple: [NBA luxury tax, calculatedPer, dollar above tax threshold]
-
A.
calculated
Indicates that one entity has determined or computed a value, result, or outcome based on information from another entity.
-
B.
calculatedOn
chosen
Indicates that a value, result, or outcome is computed based on or using the referenced entity as its input, basis, or context.
-
C.
calculationType
Indicates the specific method, formula, or approach used to perform a calculation in the described relationship.
-
D.
calibratedIn
Indicates that an instrument, device, or measurement process has been adjusted or verified to ensure accuracy according to a specified standard, environment, or unit system.
-
E.
isPer
Indicates that the subject entity is classified as a person.
- 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b2d607c81909511761b5563ddee |
completed | April 28, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69e71b4dcc408190a30429fb08fcf39e |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 8:37 p.m.