Triple
T8801868
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeremih |
E209427
|
entity |
| Predicate | notableSingle |
P3283
|
FINISHED |
| Object | Down on Me |
E759117
|
NE 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: Down on Me | Statement: [Jeremih, notableSingle, Down on Me]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Down on Me Context triple: [Jeremih, notableSingle, Down on Me]
-
A.
Down on Me
chosen
"Down on Me" is a popular R&B/hip-hop single by Jeremih featuring 50 Cent that gained widespread radio play in the early 2010s.
-
B.
Stay Down
"Stay Down" is a track by American rapper Big Sean from his critically acclaimed 2015 album *Dark Sky Paradise*.
-
C.
I’m Down
"I’m Down" is a song featured on Aerosmith’s 1987 hard rock album "Permanent Vacation."
-
D.
Get Down
"Get Down" is a 1994 hip hop single by Craig Mack, best known for its remix featuring The Notorious B.I.G. and its classic Bad Boy Records sound.
-
E.
When I’m Down
"When I’m Down" is a melancholic, jazz-tinged song by Chris Cornell that showcases his soulful vocals and introspective songwriting.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca836320e48190b5cf585b90a322c4 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5fb9c5c88190881b069e1face10c |
completed | March 31, 2026, 11:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf891583d48190ba276b5a1f7d6f7a |
completed | April 3, 2026, 9:32 a.m. |
Created at: March 30, 2026, 6:44 p.m.