Triple

T2645815
Position Surface form Disambiguated ID Type / Status
Subject Jerry Lewis E62979 entity
Predicate spouse P13 FINISHED
Object SanDee Pitnick
SanDee Pitnick is an American former dancer and actress best known as the second wife of comedian and filmmaker Jerry Lewis.
 E285506 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: SanDee Pitnick | Statement: [Jerry Lewis, spouse, SanDee Pitnick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SanDee Pitnick
Context triple: [Jerry Lewis, spouse, SanDee Pitnick]
  • A. Dana DeMuth
    Dana DeMuth is a longtime Major League Baseball umpire who has officiated numerous postseason games, including multiple World Series.
  • B. Kim Keever
    Kim Keever is an American artist and photographer known for his large-scale, otherworldly landscape images created by photographing paint and materials suspended in water.
  • C. Tracy Benchley
    Tracy Benchley is a child of American author and screenwriter Peter Benchley, best known for writing the novel "Jaws."
  • D. Dee Dee Rescher
    Dee Dee Rescher is an American character actress and voice actress known for her work in animated films and television series.
  • E. Jody Patton
    Jody Patton is an American arts and museum professional best known for co-founding Seattle’s Experience Music Project (now MoPOP) alongside Paul Allen.
  • 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: SanDee Pitnick
Triple: [Jerry Lewis, spouse, SanDee Pitnick]
Generated description
SanDee Pitnick is an American former dancer and actress best known as the second wife of comedian and filmmaker Jerry Lewis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SanDee Pitnick
Target entity description: SanDee Pitnick is an American former dancer and actress best known as the second wife of comedian and filmmaker Jerry Lewis.
  • A. Dana DeMuth
    Dana DeMuth is a longtime Major League Baseball umpire who has officiated numerous postseason games, including multiple World Series.
  • B. Kim Keever
    Kim Keever is an American artist and photographer known for his large-scale, otherworldly landscape images created by photographing paint and materials suspended in water.
  • C. Tracy Benchley
    Tracy Benchley is a child of American author and screenwriter Peter Benchley, best known for writing the novel "Jaws."
  • D. Dee Dee Rescher
    Dee Dee Rescher is an American character actress and voice actress known for her work in animated films and television series.
  • E. Jody Patton
    Jody Patton is an American arts and museum professional best known for co-founding Seattle’s Experience Music Project (now MoPOP) alongside Paul Allen.
  • 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_69ab4c3f2dcc819082df80f5e032f690 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abd91846b4819093a063c15e1ee6af completed March 7, 2026, 7:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69af98c50d108190b716dd51c34d3759 completed March 10, 2026, 4:06 a.m.
NEDg Description generation batch_69af9952a95881908d01aa13f5feef43 completed March 10, 2026, 4:08 a.m.
NED2 Entity disambiguation (via description) batch_69af99e68f10819094d758d3a4bc2e9c completed March 10, 2026, 4:11 a.m.
Created at: March 6, 2026, 9:53 p.m.