Triple

T20947749
Position Surface form Disambiguated ID Type / Status
Subject Joe DeRita E515895 entity
Predicate alsoKnownAs P39 FINISHED
Object Curly Joe DeRita
Curly Joe DeRita was an American comedian and actor best known as the later member of The Three Stooges who replaced Joe Besser in the popular slapstick comedy team.
E1459096 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: Curly Joe DeRita | Statement: [Joe DeRita, alsoKnownAs, Curly Joe DeRita]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Curly Joe DeRita
Context triple: [Joe DeRita, alsoKnownAs, Curly Joe DeRita]
  • A. John Curly
    John Curly is a technology executive best known as a co-founder of EMC Corporation, a major data storage and information management company.
  • B. Joe D'Arco
    Joe D'Arco is a musician best known as a former member of the American rock band Godsmack.
  • C. Jack Sharkey
    Jack Sharkey was an American heavyweight boxer and former world champion active in the 1920s and 1930s.
  • D. Louie De Palma
    Louie De Palma is the abrasive, scheming dispatcher portrayed by Danny DeVito in the classic television sitcom "Taxi."
  • E. Joe E. Brown
    Joe E. Brown was a popular American comedian and film actor of the 1930s and 1940s, known for his wide-mouthed grin and roles in numerous Hollywood comedies.
  • 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: Curly Joe DeRita
Triple: [Joe DeRita, alsoKnownAs, Curly Joe DeRita]
Generated description
Curly Joe DeRita was an American comedian and actor best known as the later member of The Three Stooges who replaced Joe Besser in the popular slapstick comedy team.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Curly Joe DeRita
Target entity description: Curly Joe DeRita was an American comedian and actor best known as the later member of The Three Stooges who replaced Joe Besser in the popular slapstick comedy team.
  • A. John Curly
    John Curly is a technology executive best known as a co-founder of EMC Corporation, a major data storage and information management company.
  • B. Joe D'Arco
    Joe D'Arco is a musician best known as a former member of the American rock band Godsmack.
  • C. Jack Sharkey
    Jack Sharkey was an American heavyweight boxer and former world champion active in the 1920s and 1930s.
  • D. Louie De Palma
    Louie De Palma is the abrasive, scheming dispatcher portrayed by Danny DeVito in the classic television sitcom "Taxi."
  • E. Joe E. Brown
    Joe E. Brown was a popular American comedian and film actor of the 1930s and 1940s, known for his wide-mouthed grin and roles in numerous Hollywood comedies.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadab7708190bb3a10bdd3f32d90 completed April 21, 2026, 4:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09278afe48819093d5ed09a15df594 completed May 17, 2026, 2:27 a.m.
NEDg Description generation batch_6a092849ffcc8190acd608b30edcf5d1 completed May 17, 2026, 2:30 a.m.
NED2 Entity disambiguation (via description) batch_6a0929485ebc8190ab8bc316b3e802ca completed May 17, 2026, 2:34 a.m.
Created at: April 16, 2026, 12:58 p.m.