Triple
T24039588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meyerbeer’s L’Africaine |
E595333
|
entity |
| Predicate | roleVoiceType |
P2000
|
FINISHED |
| Object | Vasco de Gama – tenor |
—
|
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: Vasco de Gama – tenor | Statement: [Meyerbeer’s L’Africaine, roleVoiceType, Vasco de Gama – tenor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleVoiceType Context triple: [Meyerbeer’s L’Africaine, roleVoiceType, Vasco de Gama – tenor]
-
A.
voiceType
chosen
Indicates the specific vocal style, quality, or role associated with an entity’s voice in a given context.
-
B.
voiceTexture
Indicates the characteristic quality or timbre of a voice as perceived in sound.
-
C.
voiceAppearance
Indicates that one entity’s voice is present, heard, or featured in association with another entity (such as a work, scene, or medium).
-
D.
voiceActingType
Indicates the specific style or category of voice performance used in an audio-visual work or production.
-
E.
voiceEffectsBy
Indicates that one entity applies or produces voice-related effects that modify or transform the voice of another entity.
- 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_69e288c06a908190899cad4531f32c9a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d8d7a51c8190b108a4f862843209 |
completed | April 29, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:57 p.m.