Triple
T3777939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viktor Petrenko |
E83351
|
entity |
| Predicate | Olympic sport |
P15215
|
FINISHED |
| Object | figure skating |
—
|
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: figure skating | Statement: [Viktor Petrenko, Olympic sport, figure skating]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Olympic sport Context triple: [Viktor Petrenko, Olympic sport, figure skating]
-
A.
OlympicGoldMedalSport
Indicates that the subject sport is one in which the object athlete or team has won an Olympic gold medal.
-
B.
OlympicStatus
chosen
Indicates that an entity holds a particular status or role in relation to the Olympic Games (e.g., being an Olympic sport, event, athlete, or host).
-
C.
sportEventType
Indicates the specific kind or category of sport associated with a given sporting event.
-
D.
olympicGames
Indicates that an entity is an edition or instance of the Olympic Games event.
-
E.
traditionalSport
Indicates that an entity is a sport practiced within a culture or community that has been passed down over generations and is recognized as part of traditional or heritage activities.
- 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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc5d3dbc8190b6ab118a56acd5a3 |
completed | March 8, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69adc050cc5c81909d9855f866f3c26d |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:36 p.m.