Triple

T9528639
Position Surface form Disambiguated ID Type / Status
Subject Charles Carroll of Carrollton E229825 entity
Predicate spouse P13 FINISHED
Object Mary Darnall E229825 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: Mary Darnall | Statement: [Charles Carroll of Carrollton, spouse, Mary Darnall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Darnall
Context triple: [Charles Carroll of Carrollton, spouse, Mary Darnall]
  • A. Mary Darnall chosen
    Mary Darnall was the wife of American Founding Father and Declaration of Independence signer Charles Carroll of Carrollton and a member of a prominent Maryland Catholic family.
  • B. Sybil Dyer
    Sybil Dyer is known primarily as the wife of Jack Dyer, the legendary Australian rules footballer and Richmond Football Club icon.
  • C. Mary Pugh
    Mary Pugh is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Pugh.
  • D. Barbara Jennings
    Barbara Jennings is the daughter of Richard Jennings.
  • E. Katharine Tennant
    Katharine Tennant was a member of the prominent Tennant family of British high society in the late 19th and early 20th centuries.
  • 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_69ca8479934c81908006d0e6e970ae05 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98b1b93481909812245ac14e4988 completed April 1, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1af4770f88190b9952c4308c0c384 completed April 5, 2026, 12:39 a.m.
Created at: March 30, 2026, 8 p.m.