Triple
T19087483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CHL Canada Russia Series |
E467188
|
entity |
| Predicate | competitionFormatDetail |
P2673
|
FINISHED |
| Object | two games hosted by each CHL league |
—
|
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: two games hosted by each CHL league | Statement: [CHL Canada Russia Series, competitionFormatDetail, two games hosted by each CHL league]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competitionFormatDetail Context triple: [CHL Canada Russia Series, competitionFormatDetail, two games hosted by each CHL league]
-
A.
competitionFormat
chosen
Indicates the specific structure or ruleset under which a competition is organized and conducted.
-
B.
tourFormat
Indicates the specific structure, style, or type of a tour associated with an entity.
-
C.
appliesToCompetitionFormat
Indicates that something is relevant or specifically designed for a particular competition format.
-
D.
replacedCompetitionFormat
Indicates that one competition format was substituted for and took the place of another competition format.
-
E.
affectedCompetitionFormat
Indicates that one entity caused a change or influence on the structure, rules, or format of a 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e348c980819096667ee6e7a7f36f |
completed | April 20, 2026, 8:26 a.m. |
| PD | Predicate disambiguation | batch_69e4b9a604308190a3235184f9f2c056 |
completed | April 19, 2026, 11:16 a.m. |
Created at: April 10, 2026, 12:04 p.m.