Triple

T4839917
Position Surface form Disambiguated ID Type / Status
Subject Mark Thatcher E108151 entity
Predicate spouse P13 FINISHED
Object Diane Burgdorf E277675 NE FINISHED

How this triple was built (2 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: Diane Burgdorf | Statement: [Mark Thatcher, spouse, Diane Burgdorf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diane Burgdorf
Context triple: [Mark Thatcher, spouse, Diane Burgdorf]
  • A. Diane Burgdorf chosen
    Diane Burgdorf is the wife of Mark Thatcher, the son of former British Prime Minister Margaret Thatcher.
  • B. Debra Christofferson
    Debra Christofferson is an American actress best known for her role as the bearded lady Lila in the HBO television series "Carnivàle."
  • C. Laura Bickford
    Laura Bickford is an American film producer best known for her work on acclaimed independent and studio films, including the Oscar-winning drama "Traffic."
  • D. Colleen Ahland
    Colleen Ahland is a linguist known for her research on the Koman languages of Ethiopia and Sudan, focusing on their documentation, description, and classification.
  • E. Cathy Shumway
    Cathy Shumway is a character from the satirical 1970s television soap opera "Mary Hartman, Mary Hartman."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd43fbe444819085cb970706ef73f7 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6cfbfbb08190b4580ebb2eb845b2 completed March 20, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141085da88190bf5cd0a90914f929 completed March 23, 2026, 1:32 p.m.
Created at: March 20, 2026, 1:25 p.m.