Triple
T28331786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Les pêcheurs de perles |
E717554
|
entity |
| Predicate | voiceTypeOfNadir |
P149434
|
FINISHED |
| Object | 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: tenor | Statement: [Les pêcheurs de perles, voiceTypeOfNadir, tenor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: voiceTypeOfNadir Context triple: [Les pêcheurs de perles, voiceTypeOfNadir, tenor]
-
A.
voiceType
Indicates the specific vocal style, quality, or role associated with an entity’s voice in a given context.
-
B.
voiceCharacter
Indicates that one entity provides the voice for, or vocally portrays, a particular character in a work.
-
C.
voiceTypeOfZoroastro
chosen
Indicates the specific vocal classification or voice type associated with the character Zoroastro.
-
D.
voiceTypeOfUlrica
Indicates that the specified voice type is the vocal classification associated with the character Ulrica.
-
E.
voiceAppearance
Indicates that one entity’s voice is present, heard, or featured in association with another entity (such as a work, scene, or medium).
- 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a931748190a637e631a52bbfaa |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 12:32 a.m.