Triple

T20590061
Position Surface form Disambiguated ID Type / Status
Subject How Pleasant It Is E505896 entity
Predicate lyricist P1360 FINISHED
Object Richard M. Sherman 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: Richard M. Sherman | Statement: [How Pleasant It Is, lyricist, Richard M. Sherman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard M. Sherman
Context triple: [How Pleasant It Is, lyricist, Richard M. Sherman]
  • A. Richard M. Sherman chosen
    Richard M. Sherman is an American songwriter best known as one half of the Sherman Brothers duo, who composed iconic music for numerous Disney films and theme park attractions.
  • B. Robert B. Sherman
    Robert B. Sherman was an American songwriter best known as one half of the Sherman Brothers duo, who wrote many iconic songs for Disney films such as "Mary Poppins" and "The Jungle Book."
  • C. Richard A. Whiting
    Richard A. Whiting was an American composer best known for writing popular standards such as "Hooray for Hollywood" and "On the Good Ship Lollipop."
  • D. Mulgrew Miller
    Mulgrew Miller was an American jazz pianist and composer renowned for his virtuosic technique, hard bop roots, and influential work as both a bandleader and sideman.
  • E. Roy Sharman
    Roy Sharman is a film editor known for his work on the 2003 adaptation of "I Capture the Castle."
  • 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_69e0b4b9669c8190b8e81fc72817d42c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a97aaf1c81908006ae7447f1f503 completed April 20, 2026, 10:32 p.m.
Created at: April 16, 2026, 11:40 a.m.