Triple
T11346778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diana Vishneva |
E268734
|
entity |
| Predicate | startTimeAtAmericanBalletTheatre |
P99369
|
FINISHED |
| Object | 2005 |
—
|
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: 2005 | Statement: [Diana Vishneva, startTimeAtAmericanBalletTheatre, 2005]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeAtAmericanBalletTheatre Context triple: [Diana Vishneva, startTimeAtAmericanBalletTheatre, 2005]
-
A.
premieredInBallet
Indicates that a work or performance had its first public presentation specifically in the context of a ballet production.
-
B.
balletInActs
Indicates that a ballet is structured or divided into a specified number of acts.
-
C.
premiereOfAdagioDate
Indicates the calendar date on which the adagio section or movement was first premiered.
-
D.
balletCompany
Indicates that one entity is a ballet company associated with, representing, or responsible for another entity (such as a performance, dancer, or production).
-
E.
hasBalletMaster
Indicates that an entity is associated with or overseen by a specific ballet master responsible for its ballet-related training, direction, or instruction.
- F. None of above. chosen
Provenance (4 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
| PDg | Predicate description generation | batch_69d801451b1c8190944b17906b354142 |
completed | April 9, 2026, 7:43 p.m. |
Created at: April 8, 2026, 9:33 p.m.