Triple

T8223315
Position Surface form Disambiguated ID Type / Status
Subject Johnny English E192116 entity
Predicate hasAlly P600 FINISHED
Object Kate Sumner
Kate Sumner is a British intelligence officer and the main female ally to the bumbling spy in the comedy film "Johnny English."
E736088 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: Kate Sumner | Statement: [Johnny English, hasAlly, Kate Sumner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Sumner
Context triple: [Johnny English, hasAlly, Kate Sumner]
  • A. Kate Garvey
    Kate Garvey is a British public relations executive and former political aide, known for her work with Tony Blair and her marriage to Wikipedia co-founder Jimmy Wales.
  • B. Brigitte Michael Sumner
    Brigitte Michael Sumner, better known as Eliot Sumner, is an English musician and actor, and the child of musician Sting and producer Trudie Styler.
  • C. Lisa Bryer
    Lisa Bryer is a British film producer best known for her work on acclaimed independent films, including the award-winning drama "The Last King of Scotland."
  • D. Sarah Sutherland
    Sarah Sutherland is an American actress best known for her role as Catherine Meyer on the HBO political satire series "Veep."
  • E. Kate Williams
    Kate Williams is a British historian, author, and television presenter known for her works on royal history and biography.
  • 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: Kate Sumner
Triple: [Johnny English, hasAlly, Kate Sumner]
Generated description
Kate Sumner is a British intelligence officer and the main female ally to the bumbling spy in the comedy film "Johnny English."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kate Sumner
Target entity description: Kate Sumner is a British intelligence officer and the main female ally to the bumbling spy in the comedy film "Johnny English."
  • A. Kate Garvey
    Kate Garvey is a British public relations executive and former political aide, known for her work with Tony Blair and her marriage to Wikipedia co-founder Jimmy Wales.
  • B. Brigitte Michael Sumner
    Brigitte Michael Sumner, better known as Eliot Sumner, is an English musician and actor, and the child of musician Sting and producer Trudie Styler.
  • C. Lisa Bryer
    Lisa Bryer is a British film producer best known for her work on acclaimed independent films, including the award-winning drama "The Last King of Scotland."
  • D. Sarah Sutherland
    Sarah Sutherland is an American actress best known for her role as Catherine Meyer on the HBO political satire series "Veep."
  • E. Kate Williams
    Kate Williams is a British historian, author, and television presenter known for her works on royal history and biography.
  • 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_69ca82c9a8ac81908b011c38698456e4 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb77cae2948190ae4507b75b5d5784 completed March 31, 2026, 7:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce391ff03c8190b10d23163bd0cfb1 completed April 2, 2026, 9:38 a.m.
NEDg Description generation batch_69ce3c354bd0819095da07133e985675 completed April 2, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_69ce3ca57ec081909a14d962eee2c9a5 completed April 2, 2026, 9:53 a.m.
Created at: March 30, 2026, 5:45 p.m.