Triple

T9231772
Position Surface form Disambiguated ID Type / Status
Subject Despicable Me 3 soundtrack E221833 entity
Predicate includesTrack P3284 FINISHED
Object Doowit
"Doowit" is a playful, upbeat song performed by Pharrell Williams for the animated film Despicable Me 3.
 E786492 NE FINISHED

How this triple was built (4 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: Doowit | Statement: [Despicable Me 3 soundtrack, includesTrack, Doowit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Doowit
Context triple: [Despicable Me 3 soundtrack, includesTrack, Doowit]
  • A. Woopi
    Woopi is the colloquial nickname for Woolgoolga, a coastal town in New South Wales, Australia known for its beaches and large Sikh community.
  • B. Dotti
    Dotti is an Italian surname most notably associated with Luca Dotti, the son of actress Audrey Hepburn.
  • C. Doozer
    Doozer is a television production company founded by Bill Lawrence, best known for producing series such as Scrubs, Cougar Town, and Ted Lasso.
  • D. Liddy
    Liddy is a surname most notably associated with G. Gordon Liddy, the former FBI agent and key figure in the Watergate scandal.
  • E. Doo-Dah
    Doo-Dah is a quirky, affectionate nickname used by locals to refer to the city of Wichita, Kansas.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Doowit
Triple: [Despicable Me 3 soundtrack, includesTrack, Doowit]
Generated description
"Doowit" is a playful, upbeat song performed by Pharrell Williams for the animated film Despicable Me 3.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Doowit
Target entity description: "Doowit" is a playful, upbeat song performed by Pharrell Williams for the animated film Despicable Me 3.
  • A. Woopi
    Woopi is the colloquial nickname for Woolgoolga, a coastal town in New South Wales, Australia known for its beaches and large Sikh community.
  • B. Dotti
    Dotti is an Italian surname most notably associated with Luca Dotti, the son of actress Audrey Hepburn.
  • C. Doozer
    Doozer is a television production company founded by Bill Lawrence, best known for producing series such as Scrubs, Cougar Town, and Ted Lasso.
  • D. Liddy
    Liddy is a surname most notably associated with G. Gordon Liddy, the former FBI agent and key figure in the Watergate scandal.
  • E. Doo-Dah
    Doo-Dah is a quirky, affectionate nickname used by locals to refer to the city of Wichita, Kansas.
  • F. None of above. chosen

Provenance (5 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_69ca83ed628c8190bc02d641e57f097f completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccee190204819096b38270a0abc116 completed April 1, 2026, 10:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077b0ed7c8190a7e8b95091033507 completed April 4, 2026, 2:30 a.m.
NEDg Description generation batch_69d0787b68ac819094acdec0ad7462ac completed April 4, 2026, 2:33 a.m.
NED2 Entity disambiguation (via description) batch_69d07900c7588190869c26dc76fe97e7 completed April 4, 2026, 2:35 a.m.
Created at: March 30, 2026, 7:29 p.m.