Triple
T38463830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toronto Defiant |
E912514
|
entity |
| Predicate | hasRosterSizeConstraint |
P21198
|
FINISHED |
| Object | Overwatch League roster rules |
—
|
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: Overwatch League roster rules | Statement: [Toronto Defiant, hasRosterSizeConstraint, Overwatch League roster rules]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRosterSizeConstraint Context triple: [Toronto Defiant, hasRosterSizeConstraint, Overwatch League roster rules]
-
A.
hasRosterSizeCategory
Indicates the classification of an entity based on the size of its roster or group of members.
-
B.
hasMaximumNumberOfMembers
chosen
Indicates that there is an upper limit on how many members can be associated with a given entity.
-
C.
sizeRestriction
Indicates that there is a limitation or constraint on the allowable size or dimensions of something in the relationship.
-
D.
hasTypicalMemberSize
Indicates the usual or characteristic size associated with members of a given class or group.
-
E.
limitedNumberOfMembers
Indicates that the associated group or entity has a maximum allowed number of members or participants.
- 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_69f76e861d8c81908559031dc66e3c15 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff16775a9881909d26dbc1f0ef3e1c |
completed | May 9, 2026, 11:11 a.m. |
| PD | Predicate disambiguation | batch_69ff158e61708190a1c581d0d306cfce |
completed | May 9, 2026, 11:07 a.m. |
Created at: May 3, 2026, 4:31 p.m.