Triple
T35147341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeffrey Buttle |
E1014878
|
entity |
| Predicate | ISUChampionship |
P81968
|
FINISHED |
| Object | Four Continents Figure Skating Championships |
—
|
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: Four Continents Figure Skating Championships | Statement: [Jeffrey Buttle, ISUChampionship, Four Continents Figure Skating Championships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ISUChampionship Context triple: [Jeffrey Buttle, ISUChampionship, Four Continents Figure Skating Championships]
-
A.
ISUChampionshipTitle
chosen
Indicates that an entity has won a championship title at an International Skating Union (ISU) competition.
-
B.
ISUChampionsSeriesFinalChampion
Indicates that an entity is the overall winner of the final event in an ISU Champions Series competition.
-
C.
EuropeanChampionInFigureSkating
Indicates that an entity has won the European championship title in figure skating.
-
D.
worldChampionInFigureSkating
Indicates that one entity holds or has held the title of world champion in the sport of figure skating.
-
E.
winnerIceDance
Indicates that one entity is the winner of an ice dance competition or event in relation to another specified context (such as a competition, year, or performance).
- 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_69f76dda7c108190a2ffd93eb6c341a7 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78cb0fe448190b8f11584fdf36c11 |
completed | May 3, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.