Triple

T23180003
Position Surface form Disambiguated ID Type / Status
Subject I Want You, I Need You, I Love You E579432 entity
Predicate lyricist P1360 FINISHED
Object Maurice Mysels 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: Maurice Mysels | Statement: [I Want You, I Need You, I Love You, lyricist, Maurice Mysels]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maurice Mysels
Context triple: [I Want You, I Need You, I Love You, lyricist, Maurice Mysels]
  • A. Maurice Mysels chosen
    Maurice Mysels was a songwriter and composer active in mid-20th-century popular music, known for contributing to romantic ballads and pop standards.
  • B. Barry Hyman
    Barry Hyman is one of the children of American literary critic and professor Stanley Edgar Hyman.
  • C. Garry Schyman
    Garry Schyman is an American composer best known for his award-winning music for video games such as the BioShock series and Middle-earth: Shadow of War.
  • D. Maurice Selwyn
    Maurice Selwyn is an actor known for appearing in the Doctor Who serial "The Krotons."
  • E. Albert Hackett
    Albert Hackett was an American playwright and screenwriter best known for co-writing classic films such as "The Thin Man" and "It's a Wonderful Life," often in collaboration with his wife Frances Goodrich.
  • 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_69e245ff8000819090d12008805315b7 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f6dad948190a64f80f2c9e8e4cb completed April 29, 2026, 4:56 a.m.
Created at: April 17, 2026, 4:04 p.m.