Triple
T20710928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Molasses to Rum |
E509035
|
entity |
| Predicate | sungToCharacters |
P21731
|
FINISHED |
| Object | Northern delegates |
—
|
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: Northern delegates | Statement: [Molasses to Rum, sungToCharacters, Northern delegates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sungToCharacters Context triple: [Molasses to Rum, sungToCharacters, Northern delegates]
-
A.
sungByCharacter
Indicates that a song or musical piece is performed vocally by a specific character.
-
B.
sungAs
chosen
Indicates that something is performed or vocalized in the manner, role, or identity specified by another entity (e.g., a song or part being sung as a particular character, style, or version).
-
C.
singerForCharacter
Indicates that one entity serves as the singing voice or vocalist for a particular character.
-
D.
characterSingersInStory
Indicates that a character performs singing within the context of a story.
-
E.
musicalCharacter
Indicates that one entity is a character or role that appears within the other entity, which is a musical work or production.
- 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1974ba08190b0e5ad529be95e4c |
completed | April 21, 2026, 12:15 a.m. |
| PD | Predicate disambiguation | batch_69e5c044d1108190b2b5d25de23f6401 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:14 p.m.