Triple
T68494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Suzanne Farrell Ballet |
E1367
|
entity |
| Predicate | repertoireIncludes |
P3738
|
FINISHED |
| Object | George Balanchine ballets |
—
|
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: George Balanchine ballets | Statement: [The Suzanne Farrell Ballet, repertoireIncludes, George Balanchine ballets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repertoireIncludes Context triple: [The Suzanne Farrell Ballet, repertoireIncludes, George Balanchine ballets]
-
A.
hasPartInDiscography
Indicates that an entity (such as a song, album, or track) is included as a component within another entity’s discography.
-
B.
reliesOnInstrument
Indicates that an action or process depends on or is carried out using a particular instrument or tool.
-
C.
hasNotableRecordingBy
Indicates that an entity (such as a work or composition) has a well-known or significant recording created or performed by a specified agent (such as an artist, ensemble, or label).
-
D.
notableArtistInCollection
Indicates that an artist is prominently represented or recognized within a particular collection.
-
E.
usesInstrument
Indicates that an agent performs an action by employing a specific instrument or tool as the means to carry it out.
- 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_69a24c06b3bc8190aa4ac89026115efc |
completed | Feb. 28, 2026, 1:59 a.m. |
| NER | Named-entity recognition | batch_69a24fd16c248190a6ee4cd96c388772 |
completed | Feb. 28, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69a24ea8cfd081908a26edad2473dde3 |
completed | Feb. 28, 2026, 2:10 a.m. |
| PDg | Predicate description generation | batch_69a24fcf5a88819088c5fa4c08476358 |
completed | Feb. 28, 2026, 2:15 a.m. |
Created at: Feb. 28, 2026, 2:03 a.m.