Triple

T8731922
Position Surface form Disambiguated ID Type / Status
Subject Howell E207275 entity
Predicate hasNotableBearer P458 FINISHED
Object Jane Howell
Jane Howell is a British television director best known for her work on series such as "Doctor Who" and various BBC dramas.
E761323 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: Jane Howell | Statement: [Howell, hasNotableBearer, Jane Howell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jane Howell
Context triple: [Howell, hasNotableBearer, Jane Howell]
  • A. Louise Howell
    Louise Howell is the psychologically tormented protagonist of the 1947 film noir "Possessed," portrayed by Joan Crawford as a woman descending into madness.
  • B. Elizabeth Howland
    Elizabeth Howland was a colonial-era New England woman known primarily as a daughter of Mayflower passenger and Plymouth Colony settler John Howland.
  • C. Anne Howells
    Anne Howells was a distinguished British mezzo-soprano renowned for her performances in opera houses worldwide during the late 20th century.
  • D. Elizabeth McDowell
    Elizabeth McDowell was the wife of American Regionalist painter and muralist Thomas Hart Benton.
  • E. Lovey Howell
    Lovey Howell is the wealthy, pampered socialite stranded on the island in the classic American TV sitcom "Gilligan's Island."
  • 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: Jane Howell
Triple: [Howell, hasNotableBearer, Jane Howell]
Generated description
Jane Howell is a British television director best known for her work on series such as "Doctor Who" and various BBC dramas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jane Howell
Target entity description: Jane Howell is a British television director best known for her work on series such as "Doctor Who" and various BBC dramas.
  • A. Louise Howell
    Louise Howell is the psychologically tormented protagonist of the 1947 film noir "Possessed," portrayed by Joan Crawford as a woman descending into madness.
  • B. Elizabeth Howland
    Elizabeth Howland was a colonial-era New England woman known primarily as a daughter of Mayflower passenger and Plymouth Colony settler John Howland.
  • C. Anne Howells
    Anne Howells was a distinguished British mezzo-soprano renowned for her performances in opera houses worldwide during the late 20th century.
  • D. Elizabeth McDowell
    Elizabeth McDowell was the wife of American Regionalist painter and muralist Thomas Hart Benton.
  • E. Lovey Howell
    Lovey Howell is the wealthy, pampered socialite stranded on the island in the classic American TV sitcom "Gilligan's Island."
  • 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_69ca8358e4008190898471a59b96c301 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d27efb88190b42d5bc9774d9c63 completed March 31, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf88dc7ba88190865957c8d344fa00 completed April 3, 2026, 9:31 a.m.
NEDg Description generation batch_69cf8bb6d7dc8190a91864130513fa4e completed April 3, 2026, 9:43 a.m.
NED2 Entity disambiguation (via description) batch_69cf8ca3e2788190a33fb28132944759 completed April 3, 2026, 9:47 a.m.
Created at: March 30, 2026, 6:37 p.m.