Triple
T69110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Hockey League |
E1381
|
entity |
| Predicate | salaryCapSystem |
P2676
|
FINISHED |
| Object | hard 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: hard salary cap | Statement: [National Hockey League, salaryCapSystem, hard salary cap]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: salaryCapSystem Context triple: [National Hockey League, salaryCapSystem, hard salary cap]
-
A.
usesSalaryCap
chosen
Indicates that an entity applies or operates under a salary cap constraint when managing compensation or payroll.
-
B.
teamRosterLimit
Indicates the maximum number of members that are allowed to be on a team’s roster.
-
C.
hasDesignatedPlayerRule
Indicates that a sports league or competition uses a designated player rule allowing certain players to be treated differently for roster or salary purposes.
-
D.
league
Indicates that an organization or team participates in, is a member of, or is associated with a particular sports or competitive league.
-
E.
relegationSystem
Indicates a system in which entities are moved to a lower tier or level based on their performance or ranking within a structured hierarchy.
- 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_69a24c06b3bc8190aa4ac89026115efc |
completed | Feb. 28, 2026, 1:59 a.m. |
| NER | Named-entity recognition | batch_69a24fd16c248190a6ee4cd96c388772 |
completed | Feb. 28, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69a24ea8cfd081908a26edad2473dde3 |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:03 a.m.