Triple
T31388989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tatiana Riabouchinska |
E800678
|
entity |
| Predicate | choreographicPartner |
P34738
|
FINISHED |
| Object | David Lichine |
—
|
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: David Lichine | Statement: [Tatiana Riabouchinska, choreographicPartner, David Lichine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: choreographicPartner Context triple: [Tatiana Riabouchinska, choreographicPartner, David Lichine]
-
A.
dancePartner
chosen
Indicates that two entities are engaged in or paired together for a dance.
-
B.
performingPartner
Indicates that one entity is the partner who participates in or carries out a performance together with another entity.
-
C.
alsoDancedAs
Indicates that an entity performed under an additional dance name or identity besides their primary one.
-
D.
choreographedTo
Indicates that one action, movement, or sequence has been deliberately designed or arranged to align in timing, pattern, or structure with another.
-
E.
choreographer
Indicates that one entity is the person who designs and arranges the dance or movement sequences performed by another entity.
- 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_69f224e9d7048190b0cc20f9071bd3e4 |
completed | April 29, 2026, 3:34 p.m. |
| NER | Named-entity recognition | batch_69f6a0ea04888190ac3a813b603bcb5c |
completed | May 3, 2026, 1:12 a.m. |
| PD | Predicate disambiguation | batch_69f69fe463248190aa78128abeab1183 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 29, 2026, 9:19 p.m.