Triple
T1291253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KHL Western Conference |
E27550
|
entity |
| Predicate | usesPointSystem |
P13495
|
FINISHED |
| Object | win–loss–overtime structure |
—
|
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: win–loss–overtime structure | Statement: [KHL Western Conference, usesPointSystem, win–loss–overtime structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesPointSystem Context triple: [KHL Western Conference, usesPointSystem, win–loss–overtime structure]
-
A.
usesCompetitionSystem
chosen
Indicates that an entity operates under or applies a particular competition system or format.
-
B.
usesNominationSystem
Indicates that an entity employs a nomination-based process to select or appoint candidates or participants.
-
C.
isScoreFor
Indicates that one value represents the score or result associated with a particular entity, event, or performance.
-
D.
ratingSystem
Indicates a system or method used to assign evaluative scores or rankings to items, actions, or entities based on defined criteria.
-
E.
rankingPoints
Indicates the number of points assigned to an entity based on its position or performance in a ranking or competition.
- 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_69a496d4ec448190ad653b2590c46711 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c0d7d15081909d3af19b9297f1cc |
completed | March 1, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69a4bee41ca08190b0ad6f7ea40c0b62 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:51 p.m.