Triple
T33946079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MLR |
E870292
|
entity |
| Predicate | rosterRegulation |
P107928
|
FINISHED |
| Object | limits on foreign players per matchday squad |
—
|
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: limits on foreign players per matchday squad | Statement: [MLR, rosterRegulation, limits on foreign players per matchday squad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rosterRegulation Context triple: [MLR, rosterRegulation, limits on foreign players per matchday squad]
-
A.
teamRosterLimit
Indicates the maximum number of members that are allowed to be on a team’s roster.
-
B.
rosterRequirement
Indicates that one entity specifies or imposes a required composition, number, or type of participants that must be included in another entity’s roster.
-
C.
competitionSquadRule
chosen
Indicates the rules or constraints governing how squads or teams must be composed or registered for a particular competition.
-
D.
rosterBasis
Indicates the underlying criterion or rule used to determine which entities are included on a particular roster.
-
E.
rosterSize
Indicates the total number of individuals included on a given roster.
- 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.