Triple

T4462710
Position Surface form Disambiguated ID Type / Status
Subject Clive James E98293 entity
Predicate spouse P13 FINISHED
Object Prue Shaw
Prue Shaw is a British Dante scholar and academic renowned for her work on Italian literature and textual criticism.
E441383 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: Prue Shaw | Statement: [Clive James, spouse, Prue Shaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prue Shaw
Context triple: [Clive James, spouse, Prue Shaw]
  • A. Thea Sharrock
    Thea Sharrock is a British theatre and film director known for her acclaimed stage productions and for directing the feature film "Me Before You."
  • B. Anita Radcliffe
    Anita Radcliffe is a kind-hearted, elegant young woman in Disney's "One Hundred and One Dalmatians," known as the human owner of Perdita and wife of Roger.
  • C. Renée Asherson
    Renée Asherson was a British stage and film actress known for her delicate, expressive performances in mid-20th-century British cinema and theatre.
  • D. Vicky Pryce
    Vicky Pryce is a Greek-born British economist known for her senior roles in UK government economic policy and for her commentary on public finance and economic reform.
  • E. Elizabeth Minshull
    Elizabeth Minshull was the third wife and later-life caretaker of the English poet John Milton, whom she married in 1663.
  • 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: Prue Shaw
Triple: [Clive James, spouse, Prue Shaw]
Generated description
Prue Shaw is a British Dante scholar and academic renowned for her work on Italian literature and textual criticism.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Prue Shaw
Target entity description: Prue Shaw is a British Dante scholar and academic renowned for her work on Italian literature and textual criticism.
  • A. Thea Sharrock
    Thea Sharrock is a British theatre and film director known for her acclaimed stage productions and for directing the feature film "Me Before You."
  • B. Anita Radcliffe
    Anita Radcliffe is a kind-hearted, elegant young woman in Disney's "One Hundred and One Dalmatians," known as the human owner of Perdita and wife of Roger.
  • C. Renée Asherson
    Renée Asherson was a British stage and film actress known for her delicate, expressive performances in mid-20th-century British cinema and theatre.
  • D. Vicky Pryce
    Vicky Pryce is a Greek-born British economist known for her senior roles in UK government economic policy and for her commentary on public finance and economic reform.
  • E. Elizabeth Minshull
    Elizabeth Minshull was the third wife and later-life caretaker of the English poet John Milton, whom she married in 1663.
  • 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_69b3454a7c608190944f5455c8031d73 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3567716a4819092a5bc9732e74592 completed March 13, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6284b90708190b557b66bd7533f4e completed March 15, 2026, 3:32 a.m.
NEDg Description generation batch_69b62954b77c8190968f844514656415 completed March 15, 2026, 3:36 a.m.
NED2 Entity disambiguation (via description) batch_69b62a0cd92c8190a9eee2a9d73fb679 completed March 15, 2026, 3:39 a.m.
Created at: March 12, 2026, 11:34 p.m.