Triple

T17948170
Position Surface form Disambiguated ID Type / Status
Subject South Swindon E448758 entity
Predicate hasMP P14470 FINISHED
Object Heidi Alexander
Heidi Alexander is a British Labour Party politician who has served as a Member of Parliament and held roles in both the Shadow Cabinet and local government.
E1327231 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: Heidi Alexander | Statement: [South Swindon, hasMP, Heidi Alexander]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heidi Alexander
Context triple: [South Swindon, hasMP, Heidi Alexander]
  • A. Heather Robertson
    Heather Robertson is the daughter of the late American actor Cliff Robertson, known for his Academy Award–winning performance in "Charly."
  • B. Heather Faulkiner
    Heather Faulkiner is known as the wife of prominent American sportscaster Marv Albert.
  • C. Deirdre Beddoe
    Deirdre Beddoe is a Welsh historian and academic known for her influential work on the history and representation of Welsh women.
  • D. Heather McIntyre
    Heather McIntyre was the wife of English actor William Hartnell, best known as the first actor to play the Doctor in the long-running BBC series Doctor Who.
  • E. Alison Marr
    Alison Marr is a mathematician known for her work in combinatorics and for her contributions to mathematics education and outreach.
  • 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: Heidi Alexander
Triple: [South Swindon, hasMP, Heidi Alexander]
Generated description
Heidi Alexander is a British Labour Party politician who has served as a Member of Parliament and held roles in both the Shadow Cabinet and local government.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Heidi Alexander
Target entity description: Heidi Alexander is a British Labour Party politician who has served as a Member of Parliament and held roles in both the Shadow Cabinet and local government.
  • A. Heather Robertson
    Heather Robertson is the daughter of the late American actor Cliff Robertson, known for his Academy Award–winning performance in "Charly."
  • B. Heather Faulkiner
    Heather Faulkiner is known as the wife of prominent American sportscaster Marv Albert.
  • C. Deirdre Beddoe
    Deirdre Beddoe is a Welsh historian and academic known for her influential work on the history and representation of Welsh women.
  • D. Heather McIntyre
    Heather McIntyre was the wife of English actor William Hartnell, best known as the first actor to play the Doctor in the long-running BBC series Doctor Who.
  • E. Alison Marr
    Alison Marr is a mathematician known for her work in combinatorics and for her contributions to mathematics education and outreach.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afa9cb2481908c95f8c430dcc0aa completed April 19, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a047125683081908a18067ff3fd7956 completed May 13, 2026, 12:40 p.m.
NEDg Description generation batch_6a04730c241c8190800aa4c99dfa5c08 completed May 13, 2026, 12:48 p.m.
NED2 Entity disambiguation (via description) batch_6a0473c5c03c8190956a5d640cfd579d completed May 13, 2026, 12:51 p.m.
Created at: April 10, 2026, 10:21 a.m.