Triple

T22226801
Position Surface form Disambiguated ID Type / Status
Subject Samuel Whiskers E549359 entity
Predicate spouse P13 FINISHED
Object Anna Maria NE NERFINISHED

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: Anna Maria | Statement: [Samuel Whiskers, spouse, Anna Maria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna Maria
Context triple: [Samuel Whiskers, spouse, Anna Maria]
  • A. Anna Maria
    Anna Maria is an Italian given name traditionally used for females, combining the names Anna and Maria.
  • B. Anna Maria chosen
    Anna Maria is a rat character from Beatrix Potter’s children’s story “The Tale of Samuel Whiskers,” known for her role in the mischievous plot involving Tom Kitten.
  • C. Anna Maria of Brunswick-Lüneburg
    Anna Maria of Brunswick-Lüneburg was a 16th-century German noblewoman and duchess from the House of Welf who became the consort of Albert, Duke of Prussia.
  • D. Anne Elisabeth
    Anne Elisabeth is a feminine given name, typically used in European countries as a compound form of Anne and Elisabeth.
  • E. Anna Catherine Constance Vasa
    Anna Catherine Constance Vasa was a Polish–Swedish princess of the Vasa dynasty, known as the daughter of King Sigismund III Vasa and a member of the early 17th-century Polish-Lithuanian royal court.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e403d6481909a94d0aaf157f6ef completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12befe38c8190b547586e41b099b1 completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:37 p.m.