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.