Triple

T23036604
Position Surface form Disambiguated ID Type / Status
Subject Christopher Fry E573612 entity
Predicate spouse P13 FINISHED
Object Phyllis Hart Fry
Phyllis Hart Fry was the wife of English poet and playwright Christopher Fry and a supportive partner throughout his literary career.
 E1567097 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: Phyllis Hart Fry | Statement: [Christopher Fry, spouse, Phyllis Hart Fry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Phyllis Hart Fry
Context triple: [Christopher Fry, spouse, Phyllis Hart Fry]
  • A. Phyllis Garr
    Phyllis Garr is the mother of American actress and comedian Teri Garr.
  • B. Phyllis Ralph
    Phyllis Ralph was the wife of English stage and film actor Lionel Atwill, known for his prominent roles in early 20th-century horror and mystery films.
  • C. Phyllis de Young
    Phyllis de Young was a member of the prominent de Young family associated with San Francisco journalism and philanthropy.
  • D. Phyllis George
    Phyllis George was an American television personality, sportscaster, and former Miss America who became one of the first prominent female hosts in sports broadcasting.
  • E. Phyllis Carlyle
    Phyllis Carlyle was a film producer best known for her work on influential 1990s movies, including the psychological thriller "Seven."
  • 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: Phyllis Hart Fry
Triple: [Christopher Fry, spouse, Phyllis Hart Fry]
Generated description
Phyllis Hart Fry was the wife of English poet and playwright Christopher Fry and a supportive partner throughout his literary career.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Phyllis Hart Fry
Target entity description: Phyllis Hart Fry was the wife of English poet and playwright Christopher Fry and a supportive partner throughout his literary career.
  • A. Phyllis Garr
    Phyllis Garr is the mother of American actress and comedian Teri Garr.
  • B. Phyllis Ralph
    Phyllis Ralph was the wife of English stage and film actor Lionel Atwill, known for his prominent roles in early 20th-century horror and mystery films.
  • C. Phyllis de Young
    Phyllis de Young was a member of the prominent de Young family associated with San Francisco journalism and philanthropy.
  • D. Phyllis George
    Phyllis George was an American television personality, sportscaster, and former Miss America who became one of the first prominent female hosts in sports broadcasting.
  • E. Phyllis Carlyle
    Phyllis Carlyle was a film producer best known for her work on influential 1990s movies, including the psychological thriller "Seven."
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1850fe5348190b42259595d82cff4 completed April 29, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2b8e994819086dbfa0936898360 completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bfbc5b19c8190aed3f1199410b996 completed May 19, 2026, 5:57 a.m.
NED2 Entity disambiguation (via description) batch_6a0bfccedf2c8190833df43ea2c294ca completed May 19, 2026, 6:01 a.m.
Created at: April 17, 2026, 3:53 p.m.