Triple

T3378658
Position Surface form Disambiguated ID Type / Status
Subject Years and Years E71126 entity
Predicate producer P490 FINISHED
Object Karen Lewis
Karen Lewis is a television producer known for her work on the British drama series "Years and Years."
 E507593 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: Karen Lewis | Statement: [Years and Years, producer, Karen Lewis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Karen Lewis
Context triple: [Years and Years, producer, Karen Lewis]
  • A. Vicki Lewis
    Vicki Lewis is an American actress and singer best known for her comedic television roles and voice work in animated films.
  • B. Dierdre Lewis
    Dierdre Lewis is a lesser-known sister of American actress and musician Juliette Lewis.
  • C. Susan Wakley
    Susan Wakley is best known as the wife of Pro Football Hall of Famer and longtime sportscaster Merlin Olsen.
  • D. Donna Harris-Lewis
    Donna Harris-Lewis is the widow of late Boston Celtics star Reggie Lewis and an advocate involved in preserving his legacy and supporting community and health-related causes.
  • 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: Karen Lewis
Triple: [Years and Years, producer, Karen Lewis]
Generated description
Karen Lewis is a television producer known for her work on the British drama series "Years and Years."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Karen Lewis
Target entity description: Karen Lewis is a television producer known for her work on the British drama series "Years and Years."
  • A. Vicki Lewis
    Vicki Lewis is an American actress and singer best known for her comedic television roles and voice work in animated films.
  • B. Dierdre Lewis
    Dierdre Lewis is a lesser-known sister of American actress and musician Juliette Lewis.
  • C. Susan Wakley
    Susan Wakley is best known as the wife of Pro Football Hall of Famer and longtime sportscaster Merlin Olsen.
  • D. Donna Harris-Lewis
    Donna Harris-Lewis is the widow of late Boston Celtics star Reggie Lewis and an advocate involved in preserving his legacy and supporting community and health-related causes.
  • 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_69ad85a7f80c8190a05e43013f298942 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb2eacb5c81908071a1dacc9a897a completed March 8, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69befe3ba3848190bcd62dd21229ca67 completed March 21, 2026, 8:23 p.m.
NEDg Description generation batch_69bf020b007881908ffc5fd50f89a309 completed March 21, 2026, 8:39 p.m.
NED2 Entity disambiguation (via description) batch_69bf02562e048190b5583f2f959b6c84 completed March 21, 2026, 8:40 p.m.
Created at: March 8, 2026, 3:14 p.m.