Triple

T20485115
Position Surface form Disambiguated ID Type / Status
Subject Charlie E502569 entity
Predicate track P17929 FINISHED
Object Smells Like Me 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: Smells Like Me | Statement: [Charlie, track, Smells Like Me]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Smells Like Me
Context triple: [Charlie, track, Smells Like Me]
  • A. Smells Like Me chosen
    "Smells Like Me" is a pop song by American singer Charlie Puth from his 2022 album "Charlie."
  • B. That Smell
    "That Smell" is a 1977 Southern rock song by Lynyrd Skynyrd, known for its cautionary lyrics about substance abuse and self-destruction.
  • C. That Smell
    "That Smell" is a politically charged, experimental novella by Egyptian writer Sonallah Ibrahim that critiques post-revolutionary Egyptian society through a fragmented, minimalist narrative.
  • D. Smells Like Children
    Smells Like Children is an EP by American rock band Marilyn Manson, best known for its dark, experimental sound and hit cover of "Sweet Dreams (Are Made of This)."
  • E. Her Smell
    Her Smell is a 2018 drama film following a self-destructive punk rock musician, portrayed by Elisabeth Moss, as she struggles with addiction, fame, and personal redemption.
  • 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_69e0b4af32848190aea80682b44d5d6e completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69b59ae2c8190bfa26a3f1e59b8d1 completed April 20, 2026, 9:32 p.m.
Created at: April 16, 2026, 11:34 a.m.