Triple

T6401287
Position Surface form Disambiguated ID Type / Status
Subject Preston Foster E144067 entity
Predicate spouse P13 FINISHED
Object Sheila Darcy
Sheila Darcy was an American film actress best known for her roles in 1930s and 1940s Hollywood B-movies and serials.
E594444 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: Sheila Darcy | Statement: [Preston Foster, spouse, Sheila Darcy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sheila Darcy
Context triple: [Preston Foster, spouse, Sheila Darcy]
  • A. Sheila Falconer
    Sheila Falconer is a British actress and choreographer best known for her long marriage to actor Patrick Stewart.
  • B. Mary Tuffley
    Mary Tuffley was the wife of English writer Daniel Defoe, known primarily through her marriage to the famed author of "Robinson Crusoe."
  • C. Margaret Allerton
    Margaret Allerton was a member of the Allerton family connected to early Plymouth Colony history through her brother, Mayflower passenger Isaac Allerton.
  • D. Clarissa Oakes
    Clarissa Oakes is a historical naval novel by Patrick O’Brian, part of the Aubrey–Maturin series following Captain Jack Aubrey and physician Stephen Maturin during the Napoleonic Wars.
  • E. Rebecca Williams
    Rebecca Williams is known primarily as the daughter of influential British moral philosopher Bernard Williams.
  • 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: Sheila Darcy
Triple: [Preston Foster, spouse, Sheila Darcy]
Generated description
Sheila Darcy was an American film actress best known for her roles in 1930s and 1940s Hollywood B-movies and serials.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sheila Darcy
Target entity description: Sheila Darcy was an American film actress best known for her roles in 1930s and 1940s Hollywood B-movies and serials.
  • A. Sheila Falconer
    Sheila Falconer is a British actress and choreographer best known for her long marriage to actor Patrick Stewart.
  • B. Mary Tuffley
    Mary Tuffley was the wife of English writer Daniel Defoe, known primarily through her marriage to the famed author of "Robinson Crusoe."
  • C. Margaret Allerton
    Margaret Allerton was a member of the Allerton family connected to early Plymouth Colony history through her brother, Mayflower passenger Isaac Allerton.
  • D. Clarissa Oakes
    Clarissa Oakes is a historical naval novel by Patrick O’Brian, part of the Aubrey–Maturin series following Captain Jack Aubrey and physician Stephen Maturin during the Napoleonic Wars.
  • E. Rebecca Williams
    Rebecca Williams is known primarily as the daughter of influential British moral philosopher Bernard Williams.
  • 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_69c008dc56fc81908d43ffcc11d73bdd completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0689ae99881909ba427769fd317ae completed March 22, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64bb2df6881908161e1a91ea103e1 completed March 27, 2026, 9:19 a.m.
NEDg Description generation batch_69c64db656a08190b278d4cd9ec45de9 completed March 27, 2026, 9:28 a.m.
NED2 Entity disambiguation (via description) batch_69c64e5cd1b88190abcdc8af02991d1d completed March 27, 2026, 9:31 a.m.
Created at: March 22, 2026, 4:35 p.m.