Triple

T8267563
Position Surface form Disambiguated ID Type / Status
Subject Donald P. Bellisario E193338 entity
Predicate spouse P13 FINISHED
Object Lynn Halpern
Lynn Halpern is known as the former wife of American television producer and screenwriter Donald P. Bellisario.
 E756199 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: Lynn Halpern | Statement: [Donald P. Bellisario, spouse, Lynn Halpern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lynn Halpern
Context triple: [Donald P. Bellisario, spouse, Lynn Halpern]
  • A. Lynne Hollander
    Lynne Hollander is an American activist best known for her involvement in the 1960s Free Speech Movement at UC Berkeley and her longtime partnership with fellow activist Mario Savio.
  • B. Beth Halper
    Beth Halper is known as the spouse of renowned American record producer and Garbage drummer Butch Vig.
  • C. Arlene Litman
    Arlene Litman was the mother of American actress Lisa Bonet.
  • D. Nancy Lieberman
    Nancy Lieberman is a pioneering American basketball player and coach, widely regarded as one of the greatest figures in women's basketball history and a trailblazer for women in the sport.
  • E. Gail Berman
    Gail Berman is an American television and film producer and media executive known for her influential roles at major studios and for producing high-profile projects across network TV and Hollywood.
  • 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: Lynn Halpern
Triple: [Donald P. Bellisario, spouse, Lynn Halpern]
Generated description
Lynn Halpern is known as the former wife of American television producer and screenwriter Donald P. Bellisario.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lynn Halpern
Target entity description: Lynn Halpern is known as the former wife of American television producer and screenwriter Donald P. Bellisario.
  • A. Lynne Hollander
    Lynne Hollander is an American activist best known for her involvement in the 1960s Free Speech Movement at UC Berkeley and her longtime partnership with fellow activist Mario Savio.
  • B. Beth Halper
    Beth Halper is known as the spouse of renowned American record producer and Garbage drummer Butch Vig.
  • C. Arlene Litman
    Arlene Litman was the mother of American actress Lisa Bonet.
  • D. Nancy Lieberman
    Nancy Lieberman is a pioneering American basketball player and coach, widely regarded as one of the greatest figures in women's basketball history and a trailblazer for women in the sport.
  • E. Gail Berman
    Gail Berman is an American television and film producer and media executive known for her influential roles at major studios and for producing high-profile projects across network TV and Hollywood.
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb794fc4208190b268bc69ff2b28a9 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cf5120159881908361bf9cb81e3932 completed April 3, 2026, 5:33 a.m.
NEDg Description generation batch_69cf52f0886881909ceb9fbe54f84d11 completed April 3, 2026, 5:41 a.m.
NED2 Entity disambiguation (via description) batch_69cf53bc19fc81908f43c3fa29bae021 completed April 3, 2026, 5:44 a.m.
Created at: March 30, 2026, 5:50 p.m.