Triple
T8271380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tatiana Tarasova |
E193435
|
entity |
| Predicate | genreOfChoreography |
P12046
|
FINISHED |
| Object | competitive figure skating programs |
—
|
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: competitive figure skating programs | Statement: [Tatiana Tarasova, genreOfChoreography, competitive figure skating programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genreOfChoreography Context triple: [Tatiana Tarasova, genreOfChoreography, competitive figure skating programs]
-
A.
choreographyStyle
chosen
Indicates the specific style or form of choreography associated with a performance, routine, or choreographic work.
-
B.
balletType
Indicates that one entity is classified as a specific type or category of ballet in relation to another entity.
-
C.
musicAndDance
Indicates a relationship where music is performed, accompanied by, or integrated with dance as a coordinated activity or event.
-
D.
danceProp
Indicates that one entity is used or involved as a prop in another entity’s dance performance or dancing activity.
-
E.
choreographedIn
Indicates that an entity (typically a choreographer or group) created or arranged the choreography for a performance, work, or event in a specified context or production.
- 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_69ca82e14ae481908ffdb822cd2192bc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7986f8cc8190a529dda980dd6e98 |
completed | March 31, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69cb70a4525481909399d313a6247ace |
completed | March 31, 2026, 6:58 a.m. |
Created at: March 30, 2026, 5:50 p.m.