Triple

T663463
Position Surface form Disambiguated ID Type / Status
Subject Vanessa Trump E12807 entity
Predicate familyName P18 FINISHED
Object Haydon
Haydon is the maiden surname of Vanessa Trump, who is known for her former marriage to Donald Trump Jr.
E88529 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: Haydon | Statement: [Vanessa Trump, familyName, Haydon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haydon
Context triple: [Vanessa Trump, familyName, Haydon]
  • A. Hayes
    Hayes is a suburban district in southeast London, England, known for its residential character and green spaces within the London Borough of Bromley.
  • B. Harrold
    Harrold is a given name and surname, used as a variant spelling of Harold.
  • C. Hale
    Hale is a village and civil parish in the Metropolitan Borough of Trafford, Greater Manchester, England, known for its affluent residential character and proximity to Altrincham.
  • D. Dyer
    Dyer is a surname most infamously associated with British officer Reginald Dyer, known for ordering the 1919 Jallianwala Bagh massacre in Amritsar, India.
  • E. Gowland
    Gowland is the middle name of Frederick Gowland Hopkins, the English biochemist and Nobel laureate known for his work on vitamins and essential nutrients.
  • 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: Haydon
Triple: [Vanessa Trump, familyName, Haydon]
Generated description
Haydon is the maiden surname of Vanessa Trump, who is known for her former marriage to Donald Trump Jr.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haydon
Target entity description: Haydon is the maiden surname of Vanessa Trump, who is known for her former marriage to Donald Trump Jr.
  • A. Hayes
    Hayes is a suburban district in southeast London, England, known for its residential character and green spaces within the London Borough of Bromley.
  • B. Harrold
    Harrold is a given name and surname, used as a variant spelling of Harold.
  • C. Hale
    Hale is a village and civil parish in the Metropolitan Borough of Trafford, Greater Manchester, England, known for its affluent residential character and proximity to Altrincham.
  • D. Dyer
    Dyer is a surname most infamously associated with British officer Reginald Dyer, known for ordering the 1919 Jallianwala Bagh massacre in Amritsar, India.
  • E. Gowland
    Gowland is the middle name of Frederick Gowland Hopkins, the English biochemist and Nobel laureate known for his work on vitamins and essential nutrients.
  • 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_69a493355dec819098d4244b2fa34885 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49fd1f0ec819087003d30bbab2fa6 completed March 1, 2026, 8:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69a654d625608190814bec3b412c86d7 completed March 3, 2026, 3:26 a.m.
NEDg Description generation batch_69a65583c7a481908b3833969c30da29 completed March 3, 2026, 3:29 a.m.
NED2 Entity disambiguation (via description) batch_69a655e1e88481909e37a9911bf5ba8c completed March 3, 2026, 3:30 a.m.
Created at: March 1, 2026, 7:36 p.m.