Triple

T20384728
Position Surface form Disambiguated ID Type / Status
Subject Roy Boulting E497929 entity
Predicate spouse P13 FINISHED
Object Diana Morgan
Diana Morgan was a British screenwriter and playwright known for her work in mid-20th-century film and theatre.
E1430589 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: Diana Morgan | Statement: [Roy Boulting, spouse, Diana Morgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Morgan
Context triple: [Roy Boulting, spouse, Diana Morgan]
  • A. Una Morgan
    Una Morgan is a Jamaican singer and keyboardist best known as a member of the Grammy-winning reggae band Morgan Heritage.
  • B. Diana Napper
    Diana Napper is a film producer best known for her work on the adaptation of "The Jane Austen Book Club."
  • C. Diana Graves
    Diana Graves is known as the wife of English character actor Michael Gough, famed for his role as Alfred in the Batman film series.
  • D. Diana Rhodes
    Diana Rhodes is the mother of American filmmaker and "Euphoria" creator Sam Levinson.
  • E. Diana Ingram
    Diana Ingram is a British quiz show contestant best known for her involvement in the "Who Wants to Be a Millionaire?" cheating scandal alongside her husband, Charles Ingram.
  • 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: Diana Morgan
Triple: [Roy Boulting, spouse, Diana Morgan]
Generated description
Diana Morgan was a British screenwriter and playwright known for her work in mid-20th-century film and theatre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Diana Morgan
Target entity description: Diana Morgan was a British screenwriter and playwright known for her work in mid-20th-century film and theatre.
  • A. Una Morgan
    Una Morgan is a Jamaican singer and keyboardist best known as a member of the Grammy-winning reggae band Morgan Heritage.
  • B. Diana Napper
    Diana Napper is a film producer best known for her work on the adaptation of "The Jane Austen Book Club."
  • C. Diana Graves
    Diana Graves is known as the wife of English character actor Michael Gough, famed for his role as Alfred in the Batman film series.
  • D. Diana Rhodes
    Diana Rhodes is the mother of American filmmaker and "Euphoria" creator Sam Levinson.
  • E. Diana Ingram
    Diana Ingram is a British quiz show contestant best known for her involvement in the "Who Wants to Be a Millionaire?" cheating scandal alongside her husband, Charles Ingram.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790a31a4819099b2e6df2bafe547 completed April 20, 2026, 7:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0883e868a88190badb2acef541f6fd completed May 16, 2026, 2:49 p.m.
NEDg Description generation batch_6a08849e605881909f3744eabf3c45ca completed May 16, 2026, 2:52 p.m.
NED2 Entity disambiguation (via description) batch_6a088511c07c81908492b7fb54609cbc completed May 16, 2026, 2:54 p.m.
Created at: April 16, 2026, 11:28 a.m.