Triple
T23227989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pavane in F-sharp minor, Op. 50 |
E581064
|
entity |
| Predicate | languageOfVocalVersion |
P47965
|
FINISHED |
| Object | French |
—
|
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: French | Statement: [Pavane in F-sharp minor, Op. 50, languageOfVocalVersion, French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfVocalVersion Context triple: [Pavane in F-sharp minor, Op. 50, languageOfVocalVersion, French]
-
A.
languageOfVocalization
chosen
Indicates the language in which a vocalization (such as speech or singing) is produced.
-
B.
hasVocalVersionTitle
Indicates that an item has a vocal version whose title is given by the associated value.
-
C.
hasVocalLanguageMix
Indicates that an entity’s vocal communication combines multiple languages or language varieties within its speech.
-
D.
vocalForm
Indicates the specific vocal or phonetic form in which something (such as a word, sound, or utterance) is expressed.
-
E.
hasVocalAdaptation
Indicates that an entity possesses a specialized vocal feature or modification that alters or enhances its sound production or communication.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192302e508190b286c284a261f172 |
completed | April 29, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:09 p.m.