Triple

T21464764
Position Surface form Disambiguated ID Type / Status
Subject In the Mood E529565 entity
Predicate lyricist P1360 FINISHED
Object Andy Razaf 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: Andy Razaf | Statement: [In the Mood, lyricist, Andy Razaf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Razaf
Context triple: [In the Mood, lyricist, Andy Razaf]
  • A. Andy Razaf chosen
    Andy Razaf was an American poet, composer, and lyricist of the Harlem Renaissance known for writing the words to numerous jazz and pop standards.
  • B. George Baquet
    George Baquet was an early New Orleans jazz clarinetist known for his influential role in the development of the genre and his work with prominent bands of the 1910s and 1920s.
  • C. Larry Groupé
    Larry Groupé is an American film and television composer known for his orchestral scores on projects ranging from feature films to documentaries and TV series.
  • D. Leroy Bach
    Leroy Bach is an American multi-instrumentalist and producer best known for his tenure in the alternative rock band Wilco during the late 1990s and early 2000s.
  • E. Bob Dorough
    Bob Dorough was an American bebop and cool jazz pianist, composer, and vocalist best known for his work on the educational TV series "Schoolhouse Rock!"
  • 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_69e0c458133481908ae8b41a12c4edec completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9e9f1b3cc819092c200f09c6f461e completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:09 p.m.