Triple
T37758392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA |
E941183
|
entity |
| Predicate | salarySystem |
P115928
|
FINISHED |
| Object | salary cap |
—
|
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: salary cap | Statement: [NBA, salarySystem, salary cap]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: salarySystem Context triple: [NBA, salarySystem, salary cap]
-
A.
salaryType
Indicates the classification or structure of compensation associated with an entity, such as whether pay is salaried, hourly, commission-based, or another type.
-
B.
salary
Indicates the amount of monetary compensation an entity receives, typically on a regular basis, for work or services performed.
-
C.
payGrade
Indicates the level or category of compensation assigned to an entity, typically reflecting its rank, role, or seniority in a pay structure.
-
D.
salaryRegulation
chosen
Indicates a regulatory relationship in which rules or policies govern the determination, adjustment, or limitation of salaries.
-
E.
doDPayGradeSystem
Indicates a relationship where an entity is assigned, managed, or evaluated according to a defined pay grade or compensation level system.
- 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_69f76ee1f3a88190834e6c8af99bccc9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaef7b6c48190b99d82da5594889c |
completed | May 6, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69fbadf632ec8190b14991c971258307 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:19 p.m.