Triple
T28262641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flower Song |
E712620
|
entity |
| Predicate | notablePerformerVoiceType |
P46281
|
FINISHED |
| Object | lyric 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: lyric tenor | Statement: [Flower Song, notablePerformerVoiceType, lyric tenor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notablePerformerVoiceType Context triple: [Flower Song, notablePerformerVoiceType, lyric tenor]
-
A.
notableCharacterVoiced
Indicates that a notable character is voiced or performed by a specific voice actor or performer.
-
B.
sungByCharacterVoiceType
Indicates that a song or vocal part is performed by a character with a specified voice type (e.g., soprano, tenor, bass).
-
C.
notableVoiceActor
Indicates that one entity is a voice actor who is especially prominent or well-known for their work on the other entity.
-
D.
hasNotableVocalType
chosen
Indicates that an entity is associated with a specific, noteworthy type or quality of vocalization or voice.
-
E.
singerVoiceActor
Indicates that the subject is both a singer and a voice actor for the object, or performs voice-acting roles in addition to singing in relation to the object.
- 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_69efb5216c6881908020dce4aea65381 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_6a00b2b425a8819091ff65695e98c3af |
completed | May 10, 2026, 4:30 p.m. |
| PD | Predicate disambiguation | batch_6a00b06efa248190b2d16b4889185119 |
completed | May 10, 2026, 4:21 p.m. |
Created at: April 27, 2026, 11:12 p.m.