Triple

T6362723
Position Surface form Disambiguated ID Type / Status
Subject Vera Drake E143148 entity
Predicate castMember P1668 FINISHED
Object Ruth Sheen
Ruth Sheen is a British actress known for her frequent collaborations with director Mike Leigh in film, television, and theatre.
E588109 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: Ruth Sheen | Statement: [Vera Drake, castMember, Ruth Sheen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Sheen
Context triple: [Vera Drake, castMember, Ruth Sheen]
  • A. Eileen Ryan
    Eileen Ryan was an American actress known for her character roles in film and television and as the mother of actor and director Sean Penn.
  • B. Annette O'Toole
    Annette O'Toole is an American actress and singer-songwriter best known for her roles in Superman-related projects, including playing Lana Lang in "Superman III" and Martha Kent on the TV series "Smallville."
  • C. Jane Roche
    Jane Roche is known as the wife of renowned Irish-American architect Kevin Roche.
  • D. Maeve Brennan
    Maeve Brennan was a British librarian and writer best known as the longtime companion and muse of poet Philip Larkin.
  • E. Helen O’Connell
    Helen O’Connell was a popular American big band singer and entertainer best known for her work with Jimmy Dorsey’s orchestra in the 1940s.
  • 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: Ruth Sheen
Triple: [Vera Drake, castMember, Ruth Sheen]
Generated description
Ruth Sheen is a British actress known for her frequent collaborations with director Mike Leigh in film, television, and theatre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ruth Sheen
Target entity description: Ruth Sheen is a British actress known for her frequent collaborations with director Mike Leigh in film, television, and theatre.
  • A. Eileen Ryan
    Eileen Ryan was an American actress known for her character roles in film and television and as the mother of actor and director Sean Penn.
  • B. Annette O'Toole
    Annette O'Toole is an American actress and singer-songwriter best known for her roles in Superman-related projects, including playing Lana Lang in "Superman III" and Martha Kent on the TV series "Smallville."
  • C. Jane Roche
    Jane Roche is known as the wife of renowned Irish-American architect Kevin Roche.
  • D. Maeve Brennan
    Maeve Brennan was a British librarian and writer best known as the longtime companion and muse of poet Philip Larkin.
  • E. Patricia O'Brien
    Patricia O'Brien is an American writer and journalist known for her collaborations with Pulitzer Prize–winning columnist Ellen Goodman and for her own works of fiction and non-fiction.
  • 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_69c008d7a9c4819098d647ec47776917 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0680c02b481908618317566e31a5c completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62d73a6ac8190a02602c3506e4226 completed March 27, 2026, 7:10 a.m.
NEDg Description generation batch_69c62f2abb7481909a8d6b6a3b07db37 completed March 27, 2026, 7:18 a.m.
NED2 Entity disambiguation (via description) batch_69c62fcd18a0819089fa5f5912f432aa completed March 27, 2026, 7:20 a.m.
Created at: March 22, 2026, 4:32 p.m.