Triple

T9328989
Position Surface form Disambiguated ID Type / Status
Subject Peter Holmes E224467 entity
Predicate hasSpouse P13 FINISHED
Object Mary Holmes
Mary Holmes is the spouse of Peter Holmes, known primarily in relation to him.
E791972 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: Mary Holmes | Statement: [Peter Holmes, hasSpouse, Mary Holmes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Holmes
Context triple: [Peter Holmes, hasSpouse, Mary Holmes]
  • A. Emily Holmes
    Emily Holmes is a Canadian actress known for her roles in film and television, including a supporting part in the thriller "Snakes on a Plane."
  • B. Eudoria Holmes
    Eudoria Holmes is the fiercely independent and unconventional mother of Enola Holmes in the "Enola Holmes" mystery series, known for her secretive activism and radical beliefs.
  • C. Amy Prentiss
    Amy Prentiss is a 1970s American television crime drama series featuring Jessica Walter as a pioneering female chief of detectives in San Francisco.
  • D. Taylor Holmes
    Taylor Holmes was an American stage and film actor active in the early to mid-20th century, known for his character roles in both silent and sound cinema.
  • E. Helen Hyslop
    Helen Hyslop was the wife of British scientist and environmentalist James Lovelock, known for supporting him during the development of his influential scientific work.
  • 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: Mary Holmes
Triple: [Peter Holmes, hasSpouse, Mary Holmes]
Generated description
Mary Holmes is the spouse of Peter Holmes, known primarily in relation to him.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Holmes
Target entity description: Mary Holmes is the spouse of Peter Holmes, known primarily in relation to him.
  • A. Emily Holmes
    Emily Holmes is a Canadian actress known for her roles in film and television, including a supporting part in the thriller "Snakes on a Plane."
  • B. Eudoria Holmes
    Eudoria Holmes is the fiercely independent and unconventional mother of Enola Holmes in the "Enola Holmes" mystery series, known for her secretive activism and radical beliefs.
  • C. Amy Prentiss
    Amy Prentiss is a 1970s American television crime drama series featuring Jessica Walter as a pioneering female chief of detectives in San Francisco.
  • D. Taylor Holmes
    Taylor Holmes was an American stage and film actor active in the early to mid-20th century, known for his character roles in both silent and sound cinema.
  • E. Helen Hyslop
    Helen Hyslop was the wife of British scientist and environmentalist James Lovelock, known for supporting him during the development of his influential scientific work.
  • 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_69ca8427a0c08190b749831d5ea98f02 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd37ab90ac8190b5c73f08dd091731 completed April 1, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0c7f345d88190912b0f10e7ab68be completed April 4, 2026, 8:12 a.m.
NEDg Description generation batch_69d0c93366c481909eca1ae2272433c9 completed April 4, 2026, 8:17 a.m.
NED2 Entity disambiguation (via description) batch_69d0c9a9e6508190815a9988bd38da9b completed April 4, 2026, 8:19 a.m.
Created at: March 30, 2026, 7:39 p.m.