Triple
T29112938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anjelika Krylova |
E736961
|
entity |
| Predicate | formerCompetitivePartner |
P122251
|
FINISHED |
| Object | Oleg Ovsyannikov |
—
|
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: Oleg Ovsyannikov | Statement: [Anjelika Krylova, formerCompetitivePartner, Oleg Ovsyannikov]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerCompetitivePartner Context triple: [Anjelika Krylova, formerCompetitivePartner, Oleg Ovsyannikov]
-
A.
partnerInCompetition
chosen
Indicates that two or more entities are collaborating as partners or teammates within the same competitive event or context.
-
B.
formerPartnerClub
Indicates that a club previously had a partnership or formal association with another club, but that relationship has since ended.
-
C.
formerPartner
Indicates that one entity was previously in a romantic or partnership relationship with another entity, but that relationship has since ended.
-
D.
formerAllyOf
Indicates that an entity was once an ally of another entity but that alliance has since ended.
-
E.
competitorOwner
Indicates that one entity owns or controls a business or asset that competes in the same market or domain as another entity’s business or asset.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69fe6739d4dc8190ae7505c089bbac29 |
completed | May 8, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69fe6541dffc81909c66a61ba69f38fc |
completed | May 8, 2026, 10:35 p.m. |
Created at: April 28, 2026, 11:20 a.m.