Triple
T28950315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albena Denkova / Maxim Staviski |
E730993
|
entity |
| Predicate | firstWorldChampionsFromCountry |
P108701
|
FINISHED |
| Object | Bulgaria |
—
|
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: Bulgaria | Statement: [Albena Denkova / Maxim Staviski, firstWorldChampionsFromCountry, Bulgaria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstWorldChampionsFromCountry Context triple: [Albena Denkova / Maxim Staviski, firstWorldChampionsFromCountry, Bulgaria]
-
A.
worldDriversChampionNationality
Indicates the nationality associated with a given world drivers champion.
-
B.
hasCountryRepresentedByWinners
Indicates that a given country is represented by one or more winners in a particular context, such as a competition or award.
-
C.
firstChampions
chosen
Indicates that the subject entities are the initial or earliest champions (winners or title holders) in a given competition, event, or context.
-
D.
dominantProducingCountryAmongWinners
Indicates the country that most frequently appears as the producing country among a given set of winners.
-
E.
worldChampionshipsGoldMedal
Indicates that the subject has won a gold medal at a world championship 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_69f043eb9bcc819091ac7b07aecb6475 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_6a00708ab11081909641d245c4282aa0 |
completed | May 10, 2026, 11:48 a.m. |
| PD | Predicate disambiguation | batch_6a00703daa0081908903ce3a28084d35 |
completed | May 10, 2026, 11:47 a.m. |
Created at: April 28, 2026, 8:43 a.m.