Triple

T8534198
Position Surface form Disambiguated ID Type / Status
Subject Rachel Johnson E202033 entity
Predicate spouse P13 FINISHED
Object Ivo Dawnay
Ivo Dawnay is a British public relations and communications professional, known for his work in politics and media circles.
E741940 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: Ivo Dawnay | Statement: [Rachel Johnson, spouse, Ivo Dawnay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ivo Dawnay
Context triple: [Rachel Johnson, spouse, Ivo Dawnay]
  • A. Ivor Richards
    Ivor Richards is an individual notable enough to be recognized as a significant bearer of the surname Richards.
  • B. Giles Wilson
    Giles Wilson is one of the sons of former British Prime Minister Harold Wilson.
  • C. Ivor Emmanuel
    Ivor Emmanuel was a Welsh singer and actor best known for his powerful baritone voice and his role leading the song "Men of Harlech" in the film Zulu.
  • D. Ivor Cutler
    Ivor Cutler was a Scottish poet, songwriter, and eccentric performer known for his surreal, deadpan humor and distinctive harmonium-accompanied spoken-word pieces.
  • E. Ivor Claire
    Ivor Claire is a central, morally complex army officer in Evelyn Waugh’s *Sword of Honour* trilogy, whose actions and choices embody the themes of honor, duty, and betrayal in wartime.
  • 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: Ivo Dawnay
Triple: [Rachel Johnson, spouse, Ivo Dawnay]
Generated description
Ivo Dawnay is a British public relations and communications professional, known for his work in politics and media circles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ivo Dawnay
Target entity description: Ivo Dawnay is a British public relations and communications professional, known for his work in politics and media circles.
  • A. Ivor Richards
    Ivor Richards is an individual notable enough to be recognized as a significant bearer of the surname Richards.
  • B. Giles Wilson
    Giles Wilson is one of the sons of former British Prime Minister Harold Wilson.
  • C. Ivor Emmanuel
    Ivor Emmanuel was a Welsh singer and actor best known for his powerful baritone voice and his role leading the song "Men of Harlech" in the film Zulu.
  • D. Ivor Cutler
    Ivor Cutler was a Scottish poet, songwriter, and eccentric performer known for his surreal, deadpan humor and distinctive harmonium-accompanied spoken-word pieces.
  • E. Ivor Claire
    Ivor Claire is a central, morally complex army officer in Evelyn Waugh’s *Sword of Honour* trilogy, whose actions and choices embody the themes of honor, duty, and betrayal in wartime.
  • 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_69ca832355b08190b8b6a4ab4a4a3554 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6a0ccd4819097b41d0dfb1c5018 completed March 31, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d7aa3a881909bfdd3536dbc4ec7 completed April 2, 2026, 1:22 p.m.
NEDg Description generation batch_69ce6ee1bae4819099ef302138599b34 completed April 2, 2026, 1:28 p.m.
NED2 Entity disambiguation (via description) batch_69ce6fb93fd88190bc53a925473f9b71 completed April 2, 2026, 1:31 p.m.
Created at: March 30, 2026, 6:17 p.m.