Triple

T5239595
Position Surface form Disambiguated ID Type / Status
Subject Mary Churchill E118305 entity
Predicate child P120 FINISHED
Object Charlotte Soames E28580 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: Charlotte Soames | Statement: [Mary Churchill, child, Charlotte Soames]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charlotte Soames
Context triple: [Mary Churchill, child, Charlotte Soames]
  • A. Mary Soames chosen
    Mary Soames was a British author and public figure best known as the youngest daughter and biographer of Winston and Clementine Churchill.
  • B. Elizabeth Erving
    Elizabeth Erving was the wife of American statesman and Massachusetts governor James Bowdoin, connecting her to a prominent colonial New England political family.
  • C. Mary Forth
    Mary Forth was the first wife of John Winthrop, the future governor of the Massachusetts Bay Colony, and a member of the English gentry in the early 17th century.
  • D. Clarissa Selwynne
    Clarissa Selwynne was a British-born character actress of the early 20th century, known for her supporting roles in silent and early sound films.
  • E. Victoria Waterfield
    Victoria Waterfield is a Victorian-era companion of the Second Doctor in the long-running British science fiction television series Doctor Who.
  • 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_69bd4467db0881909b3b0982df32cc8f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b2a52fc8190a22631e1853c74a3 completed March 20, 2026, 4:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69bef823afd88190a3a41e7fff09d449 completed March 21, 2026, 7:57 p.m.
Created at: March 20, 2026, 1:49 p.m.