Triple

T9395091
Position Surface form Disambiguated ID Type / Status
Subject Katharine Graham E226122 entity
Predicate spouse P13 FINISHED
Object Philip Graham E412113 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: Philip Graham | Statement: [Katharine Graham, spouse, Philip Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philip Graham
Context triple: [Katharine Graham, spouse, Philip Graham]
  • A. Gordon Clapp
    Gordon Clapp is an American actor best known for his Emmy-winning role as Detective Greg Medavoy on the television series "NYPD Blue."
  • B. David Graham
    David Graham is a voice actor best known for narrating the iconic 1984 Super Bowl commercial that introduced Apple’s Macintosh computer.
  • C. Philip Merrill
    Philip Merrill was an American publisher, diplomat, and philanthropist known for his leadership of The Washingtonian magazine and his significant support of journalism and higher education.
  • D. Philip L. Graham chosen
    Philip L. Graham was an influential American newspaper publisher who led The Washington Post to national prominence in the mid-20th century.
  • E. Donald E. Graham
    Donald E. Graham is an American businessman and publisher best known for leading The Washington Post through significant periods of journalistic and corporate transformation.
  • 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_69ca842f7e3481908bf5bcf52e032dbd completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd5112faa08190a8dd2c461d1e7a14 completed April 1, 2026, 5:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d107949fe4819089f68a2c368af82f completed April 4, 2026, 12:44 p.m.
Created at: March 30, 2026, 7:45 p.m.