Triple
T4266285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KHL Junior Draft |
E96831
|
entity |
| Predicate | selectionRights |
P5532
|
FINISHED |
| Object | KHL teams obtain rights to drafted players |
—
|
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: KHL teams obtain rights to drafted players | Statement: [KHL Junior Draft, selectionRights, KHL teams obtain rights to drafted players]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: selectionRights Context triple: [KHL Junior Draft, selectionRights, KHL teams obtain rights to drafted players]
-
A.
selectionRight
Indicates that one entity is chosen or designated as the correct or preferred option among a set of possible selections.
-
B.
rightsInclude
Indicates that one set of rights encompasses, contains, or subsumes another set of rights.
-
C.
restrictedRight
Indicates that an entity’s ability to exercise a particular right is limited, constrained, or subject to specific conditions or prohibitions.
-
D.
rights
chosen
Indicates that an entity possesses entitlements, permissions, or legal/moral claims in relation to another entity or context.
-
E.
establishesRight
Indicates that one entity creates or confers a legal or formal entitlement or privilege upon another entity.
- 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_69b34543f06c8190915ebb1a4574ffa9 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34fcc383c81908e17da7cbc86a630 |
completed | March 12, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_69b347f8dcb08190a725c1f7fb5a7466 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:07 p.m.