Triple
T24780410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brahms Waltzes |
E619979
|
entity |
| Predicate | composerOfMusicUsed |
P47024
|
FINISHED |
| Object | Johannes Brahms |
—
|
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: Johannes Brahms | Statement: [Brahms Waltzes, composerOfMusicUsed, Johannes Brahms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: composerOfMusicUsed Context triple: [Brahms Waltzes, composerOfMusicUsed, Johannes Brahms]
-
A.
composedForMusicBy
Indicates that a musical work was specifically created or written by a particular composer.
-
B.
producedComposer
Indicates that one entity served as the producer for a musical work created or composed by another entity.
-
C.
musicOrchestratedBy
Indicates that a piece of music or musical work is arranged or orchestrated by a specific person or entity.
-
D.
hasMusicalComposer
chosen
Indicates that one entity serves as the musical composer responsible for creating the music associated with another entity.
-
E.
musicUsed
Indicates that one entity makes use of or incorporates another entity as music, such as in a performance, production, or media context.
- 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_69e2fabdbe8c8190adbb9434b8636cad |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f47b865df48190bf4b6d3e9f9305e6 |
completed | May 1, 2026, 10:08 a.m. |
| PD | Predicate disambiguation | batch_69f4682c8a3c8190adbfaac99474eaaf |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 18, 2026, 4:44 a.m.