Triple
T27347402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Rondo à la Turk |
E684265
|
entity |
| Predicate | originalPianist |
P85583
|
FINISHED |
| Object | Dave Brubeck |
—
|
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: Dave Brubeck | Statement: [Blue Rondo à la Turk, originalPianist, Dave Brubeck]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalPianist Context triple: [Blue Rondo à la Turk, originalPianist, Dave Brubeck]
-
A.
firstPerformerPiano
Indicates that the referenced entity is the first (primary or earliest) performer on the piano in a given performance or musical context.
-
B.
hasPianist
chosen
Indicates that an entity is associated with or features a pianist, typically specifying who performs the piano part in a work, event, or group.
-
C.
originalPerformer
Indicates that an entity is the first or initial performer of a work, role, or performance.
-
D.
originalConductor
Indicates that an entity served as the first or initial conductor responsible for leading or directing a particular performance, ensemble, or musical work.
-
E.
performsOriginalMusic
Indicates that an entity presents or plays music that it has created itself, rather than covering or reproducing others’ works.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fdd2be648c8190b60b3d1caeb44364 |
completed | May 8, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69fdd14a5c708190a6f95ec61f4fc28f |
completed | May 8, 2026, 12:04 p.m. |
Created at: April 27, 2026, 11:46 a.m.