Triple

T16398924
Position Surface form Disambiguated ID Type / Status
Subject Susanna Philipse E398257 entity
Predicate spouse P13 FINISHED
Object Beverley Robinson E1215560 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: Beverley Robinson | Statement: [Susanna Philipse, spouse, Beverley Robinson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beverley Robinson
Context triple: [Susanna Philipse, spouse, Beverley Robinson]
  • A. Beverley Robinson chosen
    Beverley Robinson was an 18th-century New York Loyalist landowner and military officer who supported the British during the American Revolutionary War.
  • B. Beverley Mitchell
    Beverley Mitchell is an American actress best known for playing Lucy Camden on the long-running family drama series "7th Heaven."
  • C. Mavis Batey
    Mavis Batey was a British codebreaker at Bletchley Park during World War II who played a key role in deciphering enemy communications, and later became a noted garden historian and author.
  • D. Yvonne Roberts
    Yvonne Roberts is a British journalist and writer known for her work on social issues, politics, and feminism.
  • E. Beverly Owens
    Beverly Owens is an American actress best known for originating the role of Marilyn Munster on the 1960s television sitcom "The Munsters."
  • 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_69d87f2950248190bc8ad9b9bebdc8c8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e327cdc62481909de144b09a921e63 completed April 18, 2026, 6:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00581245108190842cfd68ec640236 completed May 10, 2026, 10:04 a.m.
Created at: April 10, 2026, 5:09 a.m.