Triple

T7221967
Position Surface form Disambiguated ID Type / Status
Subject Grant Shapps E150279 entity
Predicate hasAlias P455 FINISHED
Object Corinne Stockheath
Corinne Stockheath is a pseudonym used by British Conservative politician Grant Shapps.
 E692600 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: Corinne Stockheath | Statement: [Grant Shapps, hasAlias, Corinne Stockheath]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Corinne Stockheath
Context triple: [Grant Shapps, hasAlias, Corinne Stockheath]
  • A. Corinne Kingsbury
    Corinne Kingsbury is an American television writer and producer known for creating the series "In the Dark" and "Fam."
  • B. Corinne Day
    Corinne Day was a British fashion and documentary photographer known for her raw, unvarnished style that helped define the 1990s "heroin chic" aesthetic and launched the career of model Kate Moss.
  • C. Michelle Mylett
    Michelle Mylett is a Canadian actress best known for playing Katy on the comedy series "Letterkenny."
  • D. Rebecca Cottrell
    Rebecca Cottrell is the wife of Stephen Cottrell, the Archbishop of York in the Church of England.
  • E. Shannon Doughton
    Shannon Doughton is a musician best known as a principal performer associated with the band Pod.
  • 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: Corinne Stockheath
Triple: [Grant Shapps, hasAlias, Corinne Stockheath]
Generated description
Corinne Stockheath is a pseudonym used by British Conservative politician Grant Shapps.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Corinne Stockheath
Target entity description: Corinne Stockheath is a pseudonym used by British Conservative politician Grant Shapps.
  • A. Corinne Kingsbury
    Corinne Kingsbury is an American television writer and producer known for creating the series "In the Dark" and "Fam."
  • B. Corinne Day
    Corinne Day was a British fashion and documentary photographer known for her raw, unvarnished style that helped define the 1990s "heroin chic" aesthetic and launched the career of model Kate Moss.
  • C. Michelle Mylett
    Michelle Mylett is a Canadian actress best known for playing Katy on the comedy series "Letterkenny."
  • D. Rebecca Cottrell
    Rebecca Cottrell is the wife of Stephen Cottrell, the Archbishop of York in the Church of England.
  • E. Shannon Doughton
    Shannon Doughton is a musician best known as a principal performer associated with the band Pod.
  • 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_69c687effb44819092b95d07d0368c9f completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e9b42c5c81908c405f161c35ffb4 completed March 27, 2026, 8:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69ca65545c3c819080a4bf7945871e5d completed March 30, 2026, 11:58 a.m.
NEDg Description generation batch_69ca65d0dc908190917389d02ce71c2a completed March 30, 2026, noon
NED2 Entity disambiguation (via description) batch_69ca663ff0b88190af78d7e32ca1c003 completed March 30, 2026, 12:02 p.m.
Created at: March 27, 2026, 2:54 p.m.