Triple
T24407501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014–15 KHL season |
E615352
|
entity |
| Predicate | finalsOpponentOfChampion |
P108808
|
FINISHED |
| Object | Ak Bars Kazan |
—
|
NE NERFINISHED |
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: Ak Bars Kazan | Statement: [2014–15 KHL season, finalsOpponentOfChampion, Ak Bars Kazan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalsOpponentOfChampion Context triple: [2014–15 KHL season, finalsOpponentOfChampion, Ak Bars Kazan]
-
A.
finalsChampion
Indicates that an entity is the winner or champion of a particular final match, series, or tournament.
-
B.
finalChampion
Indicates that an entity is the ultimate winner or last remaining champion in a competition or series of contests.
-
C.
finalOpponentOf
chosen
Indicates that one entity serves as the last or ultimate opponent faced by another entity in a sequence of confrontations or competitions.
-
D.
worldChampionPredecessor
Indicates that one entity was the immediate previous world champion before another entity.
-
E.
championFinalsRecord
Indicates the win–loss record a champion has specifically in finals appearances.
- 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_69e2d7e780bc81908049c779e697a7f6 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2957e8d5c8190bfed93aa308eb523 |
completed | April 29, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69f287cc4fd4819081e93cc638d9512d |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:05 a.m.