Triple
T19552853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Up (song) |
E489234
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Yung Dza |
—
|
NE NERFINISHED |
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: Yung Dza | Statement: [Up (song), producer, Yung Dza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yung Dza Context triple: [Up (song), producer, Yung Dza]
-
A.
Yung Dza
chosen
Yung Dza is a songwriter and music artist known for contributing to contemporary tracks such as the song "Up."
-
B.
Yung Gud
Yung Gud is a Swedish producer and DJ best known for his atmospheric, melancholic beats and frequent collaborations with rapper Yung Lean as part of the Sad Boys collective.
-
C.
Yung Ro
Yung Ro is an American rapper best known as a member of Chamillionaire’s Houston-based hip hop group The Color Changin' Click.
-
D.
Yandel
Yandel is a Puerto Rican reggaeton singer and songwriter best known as one half of the duo Wisin & Yandel and for his influential solo work in Latin urban music.
-
E.
Yung Joc
Yung Joc is an American rapper from Atlanta best known for his mid-2000s hit single "It's Goin' Down" and his contributions to Southern hip hop.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d315c68819087402802d624a8c9 |
completed | April 20, 2026, 2:50 p.m. |
Created at: April 10, 2026, 1:41 p.m.