Triple

T16317862
Position Surface form Disambiguated ID Type / Status
Subject Top of the Heap E396217 entity
Predicate starring P1507 FINISHED
Object Leslie Bega
Leslie Bega is an American actress best known for her roles on television series such as "Head of the Class" and "The Sopranos."
E1230507 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: Leslie Bega | Statement: [Top of the Heap, starring, Leslie Bega]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leslie Bega
Context triple: [Top of the Heap, starring, Leslie Bega]
  • A. Daniela Ruah
    Daniela Ruah is a Portuguese-American actress best known for playing Special Agent Kensi Blye on the television series "NCIS: Los Angeles."
  • B. Maya Van Dien
    Maya Van Dien is the daughter of American actress Catherine Oxenberg and actor Casper Van Dien.
  • C. Lara Flynn Boyle
    Lara Flynn Boyle is an American actress best known for her role as Donna Hayward in the television series "Twin Peaks" and for her work in films and other TV dramas throughout the 1990s and 2000s.
  • D. Rebecca Tilly
    Rebecca Tilly is a member of the Tilly family and the sister of actress and author Meg Tilly.
  • E. Melissa Cobb
    Melissa Cobb is an American film producer best known for her work on major animated features, including the Kung Fu Panda franchise.
  • 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: Leslie Bega
Triple: [Top of the Heap, starring, Leslie Bega]
Generated description
Leslie Bega is an American actress best known for her roles on television series such as "Head of the Class" and "The Sopranos."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Leslie Bega
Target entity description: Leslie Bega is an American actress best known for her roles on television series such as "Head of the Class" and "The Sopranos."
  • A. Daniela Ruah
    Daniela Ruah is a Portuguese-American actress best known for playing Special Agent Kensi Blye on the television series "NCIS: Los Angeles."
  • B. Maya Van Dien
    Maya Van Dien is the daughter of American actress Catherine Oxenberg and actor Casper Van Dien.
  • C. Lara Flynn Boyle
    Lara Flynn Boyle is an American actress best known for her role as Donna Hayward in the television series "Twin Peaks" and for her work in films and other TV dramas throughout the 1990s and 2000s.
  • D. Rebecca Tilly
    Rebecca Tilly is a member of the Tilly family and the sister of actress and author Meg Tilly.
  • E. Melissa Cobb
    Melissa Cobb is an American film producer best known for her work on major animated features, including the Kung Fu Panda franchise.
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e296b31b988190bb1fde36dae11bbd completed April 17, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a009d27712081908530bbf0d9d47e1f completed May 10, 2026, 2:58 p.m.
NEDg Description generation batch_6a009e1aa6548190b77def9f74d3272a completed May 10, 2026, 3:02 p.m.
NED2 Entity disambiguation (via description) batch_6a009eb06d6481909914286301f9b4db completed May 10, 2026, 3:05 p.m.
Created at: April 10, 2026, 5:06 a.m.