Triple
T23763002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | One in a Million (Ne-Yo song) |
E587301
|
entity |
| Predicate | hasChoreographyInMusicVideo |
P35114
|
FINISHED |
| Object | Yes |
—
|
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: Yes | Statement: [One in a Million (Ne-Yo song), hasChoreographyInMusicVideo, Yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChoreographyInMusicVideo Context triple: [One in a Million (Ne-Yo song), hasChoreographyInMusicVideo, Yes]
-
A.
hasChoreographedDanceInVideo
Indicates that an entity has created or arranged the choreography for a dance that appears in a particular video.
-
B.
hasDanceChoreography
Indicates that an entity is associated with or characterized by a specific dance choreography.
-
C.
hasChoreographyBasedOn
Indicates that one choreography is derived from, inspired by, or structured according to another existing work or source.
-
D.
hasDanceSceneWith
Indicates that two entities participate together in a dance scene within the same context or work.
-
E.
hasDanceSequences
chosen
Indicates that the subject contains or features one or more dance sequences as part of its content or activity.
- 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_69e2490b8ac48190a6b35f1d5500486b |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bdb40ee881908f3916cc6d05fc72 |
completed | April 29, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:14 p.m.