Triple

T4043682
Position Surface form Disambiguated ID Type / Status
Subject Drop Dead Diva E84011 entity
Predicate starring P1507 FINISHED
Object Kate Levering
Kate Levering is an American actress best known for her role as the driven attorney Kim Kaswell on the television series "Drop Dead Diva."
E525727 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: Kate Levering | Statement: [Drop Dead Diva, starring, Kate Levering]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Levering
Context triple: [Drop Dead Diva, starring, Kate Levering]
  • A. Karen Lewis
    Karen Lewis is a television producer known for her work on the British drama series "Years and Years."
  • B. Kathryn Morris
    Kathryn Morris is an American actress best known for her lead role as Detective Lilly Rush on the television series "Cold Case."
  • C. Mary Cunningham
    Mary Cunningham is known as the spouse of Welsh actor Clive Merrison, recognized for his extensive work in British television, film, and radio drama.
  • D. Maryanne Vollers
    Maryanne Vollers is an American author, journalist, and ghostwriter known for collaborating on high-profile political and human rights memoirs.
  • E. Linda Banwell
    Linda Banwell is best known as the wife of the late English actor and director Bob Hoskins.
  • 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: Kate Levering
Triple: [Drop Dead Diva, starring, Kate Levering]
Generated description
Kate Levering is an American actress best known for her role as the driven attorney Kim Kaswell on the television series "Drop Dead Diva."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kate Levering
Target entity description: Kate Levering is an American actress best known for her role as the driven attorney Kim Kaswell on the television series "Drop Dead Diva."
  • A. Karen Lewis
    Karen Lewis is a television producer known for her work on the British drama series "Years and Years."
  • B. Kathryn Morris
    Kathryn Morris is an American actress best known for her lead role as Detective Lilly Rush on the television series "Cold Case."
  • C. Mary Cunningham
    Mary Cunningham is known as the spouse of Welsh actor Clive Merrison, recognized for his extensive work in British television, film, and radio drama.
  • D. Maryanne Vollers
    Maryanne Vollers is an American author, journalist, and ghostwriter known for collaborating on high-profile political and human rights memoirs.
  • E. Linda Banwell
    Linda Banwell is best known as the wife of the late English actor and director Bob Hoskins.
  • 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_69aed930bd5c819083e7dcc14fc44f69 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb5d759c8190b61fbbe94ffe2bf7 completed March 9, 2026, 4:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf9ad2f8e48190aac71e657a9e1197 completed March 22, 2026, 7:31 a.m.
NEDg Description generation batch_69bf9b9dbabc81908ef4d25455616f76 completed March 22, 2026, 7:34 a.m.
NED2 Entity disambiguation (via description) batch_69bf9c45029c8190b9588a436d9804af completed March 22, 2026, 7:37 a.m.
Created at: March 9, 2026, 3:37 p.m.