Triple

T8255107
Position Surface form Disambiguated ID Type / Status
Subject John Ross E193051 entity
Predicate spouse P13 FINISHED
Object Mary Brian Stapler Ross E724081 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 Brian Stapler Ross | Statement: [John Ross, spouse, Mary Brian Stapler Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Brian Stapler Ross
Context triple: [John Ross, spouse, Mary Brian Stapler Ross]
  • A. Mary Brian Stapler Ross chosen
    Mary Brian Stapler Ross was the wife of American Revolutionary War figure John Ross and a member of Philadelphia’s prominent Stapler family.
  • B. Mary Elizabeth Baird
    Mary Elizabeth Baird was the mother of Ruth Bryan Owen, the pioneering American congresswoman and diplomat.
  • C. Mary Beth Hughes
    Mary Beth Hughes was an American film and television actress best known for her roles in 1940s Hollywood dramas and crime films.
  • D. Hilary Geary Ross
    Hilary Geary Ross is an American socialite, philanthropist, and society columnist known for her prominent role in New York and Palm Beach social circles.
  • E. Kate Richards
    Kate Richards was an American socialist activist, orator, and antiwar campaigner prominent in the early 20th century labor and political movements.
  • 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_69ca82dfad9c8190b8cd18fb89f50f40 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb78f9f680819088f1d56e0f98974f completed March 31, 2026, 7:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd94f9c97881908c6e9f266aba888e completed April 1, 2026, 9:58 p.m.
Created at: March 30, 2026, 5:48 p.m.