Triple
T23459927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonata No. 4 in E minor, Op. 2 |
E568939
|
entity |
| Predicate | typicalMelodyInstruments |
P12878
|
FINISHED |
| Object | two violins |
—
|
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: two violins | Statement: [Sonata No. 4 in E minor, Op. 2, typicalMelodyInstruments, two violins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMelodyInstruments Context triple: [Sonata No. 4 in E minor, Op. 2, typicalMelodyInstruments, two violins]
-
A.
melodyType
Indicates the specific kind or category of melody associated with or used by an entity.
-
B.
typicalLeadInstrument
Indicates that an instrument is commonly used as the primary or lead instrument in a given musical context or performance.
-
C.
hasMelodyInstrument
Indicates that something uses or features a particular instrument to carry the main melody.
-
D.
musicInstrumentation
chosen
Indicates the specific instruments or instrumental forces used to perform a piece of music.
-
E.
learnedInstrument
Indicates that an entity has acquired the skill or ability to play a particular musical instrument.
- 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_69e2458ebd808190b3298163132cfb0b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a69afba88190b1b1dd27d331309f |
completed | April 29, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69f06201d33481909b5fd7b92d03e658 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 5:53 p.m.