Triple

T5257959
Position Surface form Disambiguated ID Type / Status
Subject Clarissa Hall E118747 entity
Predicate spouse P13 FINISHED
Object Leonard Jerome E164929 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: Leonard Jerome | Statement: [Clarissa Hall, spouse, Leonard Jerome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leonard Jerome
Context triple: [Clarissa Hall, spouse, Leonard Jerome]
  • A. Leonard Jerome chosen
    Leonard Jerome was a prominent 19th-century American financier and sportsman, best known as the maternal grandfather of Winston Churchill.
  • B. Leonard W. Jerome Johnson
    Leonard W. Jerome Johnson is a member of the prominent Johnson family, known for its social and historical significance.
  • C. Arthur Sheekman
    Arthur Sheekman was an American screenwriter and humorist best known for his work on Marx Brothers films and other Hollywood comedies during the 1930s and 1940s.
  • D. Leonard Rogers
    Leonard Rogers was a prominent British physician and researcher in tropical medicine, particularly known for his work in India on cholera, dysentery, and kala-azar.
  • E. Leonard Nelson
    Leonard Nelson was a German philosopher and mathematician known for reviving and developing the neo-Friesian school of critical philosophy in the early 20th century.
  • 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_69bd446978108190bb5f9c5c23d93f88 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7ba64fe48190943e7d49f6e1449a completed March 20, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf06c3945c8190874ecd184fa886a0 completed March 21, 2026, 8:59 p.m.
Created at: March 20, 2026, 1:50 p.m.