Triple

T712953
Position Surface form Disambiguated ID Type / Status
Subject Willow E14248 entity
Predicate starring P1507 FINISHED
Object Jean Marsh
Jean Marsh is an English actress and writer best known as the co-creator and star of the acclaimed television series "Upstairs, Downstairs."
E92118 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: Jean Marsh | Statement: [Willow, starring, Jean Marsh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Marsh
Context triple: [Willow, starring, Jean Marsh]
  • A. Joanna Blunt
    Joanna Blunt is the mother of British actress Emily Blunt and a member of the Blunt family connected to the entertainment industry.
  • B. Annette Kaye
    Annette Kaye is known as one of Larry King's former wives, with whom he reportedly had a brief marriage and a son.
  • C. Sheila Hancock
    Sheila Hancock is a British actress and author renowned for her extensive work in theatre, television, and film, as well as her appearances as a television presenter and panelist.
  • D. Joanne Whalley
    Joanne Whalley is an English actress known for her film and television roles, including her prominent performance in the fantasy adventure film "Willow."
  • E. Claire Bloom
    Claire Bloom is an acclaimed English actress known for her distinguished stage and screen career, including prominent roles in classic films, television dramas, and Shakespearean productions.
  • 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: Jean Marsh
Triple: [Willow, starring, Jean Marsh]
Generated description
Jean Marsh is an English actress and writer best known as the co-creator and star of the acclaimed television series "Upstairs, Downstairs."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jean Marsh
Target entity description: Jean Marsh is an English actress and writer best known as the co-creator and star of the acclaimed television series "Upstairs, Downstairs."
  • A. Joanna Blunt
    Joanna Blunt is the mother of British actress Emily Blunt and a member of the Blunt family connected to the entertainment industry.
  • B. Annette Kaye
    Annette Kaye is known as one of Larry King's former wives, with whom he reportedly had a brief marriage and a son.
  • C. Sheila Hancock
    Sheila Hancock is a British actress and author renowned for her extensive work in theatre, television, and film, as well as her appearances as a television presenter and panelist.
  • D. Joanne Whalley
    Joanne Whalley is an English actress known for her film and television roles, including her prominent performance in the fantasy adventure film "Willow."
  • E. Claire Bloom
    Claire Bloom is an acclaimed English actress known for her distinguished stage and screen career, including prominent roles in classic films, television dramas, and Shakespearean productions.
  • 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_69a4934a36e081909e7abef98b898a4e completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a55ee4fc81909358659ec3bc435f completed March 1, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69a66d9140148190a439ac7a03ee88b2 completed March 3, 2026, 5:11 a.m.
NEDg Description generation batch_69a66e046bbc8190848a0d0115dc34bd completed March 3, 2026, 5:13 a.m.
NED2 Entity disambiguation (via description) batch_69a66fdd09b081909056bff1a32d413c completed March 3, 2026, 5:21 a.m.
Created at: March 1, 2026, 7:36 p.m.