Triple

T19612538
Position Surface form Disambiguated ID Type / Status
Subject John Phillips E470768 entity
Predicate spouse P13 FINISHED
Object Susan Adams NE NERFINISHED

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: Susan Adams | Statement: [John Phillips, spouse, Susan Adams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Adams
Context triple: [John Phillips, spouse, Susan Adams]
  • A. Susan Adams chosen
    Susan Adams is the mother of American actress and singer Mackenzie Phillips.
  • B. Diana Adams
    Diana Adams was a prominent American ballerina and muse of choreographer George Balanchine, known for her leading roles with the New York City Ballet in the mid-20th century.
  • C. Sandra Adair
    Sandra Adair is an American film editor best known for her long-time collaboration with director Richard Linklater on films such as "Boyhood" and the "Before" trilogy.
  • D. Shirlee Mae Adams
    Shirlee Mae Adams is the widow of acclaimed American actor Henry Fonda, known primarily for her marriage to the Hollywood legend.
  • E. Susan Blanchard
    Susan Blanchard is an American socialite and former Broadway production assistant best known as the third wife of actor Henry Fonda.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e510fa248190b7afb274a1d4cf73 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640cbeda08190addb1adf84af4993 completed April 20, 2026, 3:05 p.m.
Created at: April 10, 2026, 1:43 p.m.