Triple
T22506000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cara sposa |
E556389
|
entity |
| Predicate | historicalVoiceType |
P135747
|
FINISHED |
| Object | castrato (originally written for castrato voice) |
—
|
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: castrato (originally written for castrato voice) | Statement: [Cara sposa, historicalVoiceType, castrato (originally written for castrato voice)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalVoiceType Context triple: [Cara sposa, historicalVoiceType, castrato (originally written for castrato voice)]
-
A.
voiceType
Indicates the specific vocal style, quality, or role associated with an entity’s voice in a given context.
-
B.
hasMusicalVocalType
chosen
Indicates that an entity is associated with a specific type or classification of singing voice.
-
C.
artisticVocalStyle
Indicates a relationship where an entity’s vocal performance is characterized by a particular artistic style or expressive manner of singing or speaking.
-
D.
characterTypeVoiced
Indicates that one character serves as the voice actor or vocal performer for another character.
-
E.
vocalGender
Indicates the perceived or assigned gender associated with an entity’s voice in a vocal performance or recording.
- 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d5bf0f0819093426d83ebd80ef0 |
completed | April 29, 2026, 1:22 a.m. |
| PD | Predicate disambiguation | batch_69e898be31448190be5ae7f5656f0497 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:50 p.m.