Triple

T6846185
Position Surface form Disambiguated ID Type / Status
Subject Phil Neville E157899 entity
Predicate spouse P13 FINISHED
Object Julie Neville
Julie Neville is a British businesswoman and nutrition expert best known as the wife of former footballer and coach Phil Neville.
E623077 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: Julie Neville | Statement: [Phil Neville, spouse, Julie Neville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julie Neville
Context triple: [Phil Neville, spouse, Julie Neville]
  • A. Phyllida Trant
    Phyllida Trant is a fellow barrister who works alongside Horace Rumpole in the same set of legal chambers in John Mortimer’s Rumpole stories.
  • B. Gillian Redfearn
    Gillian Redfearn is a prominent British science fiction and fantasy editor and publishing director, recognized for her influential work in genre publishing.
  • C. Carol Vessey
    Carol Vessey is a fictional high school teacher and love interest of the title character in the television series "Ed."
  • D. Bronwen Maddox
    Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
  • E. Carobeth Laird
    Carobeth Laird was an American ethnographer and linguist best known for her influential documentation of Chemehuevi language and culture.
  • 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: Julie Neville
Triple: [Phil Neville, spouse, Julie Neville]
Generated description
Julie Neville is a British businesswoman and nutrition expert best known as the wife of former footballer and coach Phil Neville.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Julie Neville
Target entity description: Julie Neville is a British businesswoman and nutrition expert best known as the wife of former footballer and coach Phil Neville.
  • A. Phyllida Trant
    Phyllida Trant is a fellow barrister who works alongside Horace Rumpole in the same set of legal chambers in John Mortimer’s Rumpole stories.
  • B. Gillian Redfearn
    Gillian Redfearn is a prominent British science fiction and fantasy editor and publishing director, recognized for her influential work in genre publishing.
  • C. Carol Vessey
    Carol Vessey is a fictional high school teacher and love interest of the title character in the television series "Ed."
  • D. Bronwen Maddox
    Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
  • E. Carobeth Laird
    Carobeth Laird was an American ethnographer and linguist best known for her influential documentation of Chemehuevi language and culture.
  • 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_69c6882ed4c081909dc465a7cf8838be completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d7cbe4488190b41ddf953f12f55f completed March 27, 2026, 7:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fc42e688190baa8413883e5506c completed March 28, 2026, 1:32 a.m.
NEDg Description generation batch_69c7304c0bac8190a9ece4e50ab49586 completed March 28, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69c7310fa9bc8190bfb0a43890dc5e96 completed March 28, 2026, 1:38 a.m.
Created at: March 27, 2026, 2:20 p.m.