Triple
T22213382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1984–85 NBA season |
E549011
|
entity |
| Predicate | salaryCapAmount |
P38506
|
FINISHED |
| Object | 3600000 USD |
—
|
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: 3600000 USD | Statement: [1984–85 NBA season, salaryCapAmount, 3600000 USD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: salaryCapAmount Context triple: [1984–85 NBA season, salaryCapAmount, 3600000 USD]
-
A.
salaryCapUpperLimitUSD
chosen
Indicates the maximum allowable salary amount, expressed in U.S. dollars, that an entity (such as a person, team, or organization) is permitted to pay or receive under a defined cap or budget constraint.
-
B.
usesSalaryCap
Indicates that an entity applies or operates under a salary cap constraint when managing compensation or payroll.
-
C.
averagePlayerSalary
Indicates the typical or mean salary earned by players within a specified group or context.
-
D.
subjectToAnnualCap
Indicates that the related amount, usage, or activity is limited by a maximum allowable value that applies on an annual basis.
-
E.
introducedSalaryCapSeason
Indicates the season during which a salary cap was first implemented or introduced.
- 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.