Triple

T14952753
Position Surface form Disambiguated ID Type / Status
Subject Patricia Harrison E372837 entity
Predicate name P16 FINISHED
Object Patricia Harrison E372837 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: Patricia Harrison | Statement: [Patricia Harrison, name, Patricia Harrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patricia Harrison
Context triple: [Patricia Harrison, name, Patricia Harrison]
  • A. Patricia Harrison chosen
    Patricia Harrison is an American public relations executive and former co-chair of the Republican National Committee who has served as president and CEO of the Corporation for Public Broadcasting.
  • B. Patricia Haines
    Patricia Haines was a British actress known for her television and film roles in the 1950s and 1960s.
  • C. Carole Penny Marshall
    Carole Penny Marshall was an American actress, director, and producer best known for starring in the sitcom "Laverne & Shirley" and directing hit films such as "Big" and "A League of Their Own."
  • D. Diane English
    Diane English is an American television writer and producer best known for creating the acclaimed sitcom "Murphy Brown."
  • E. Patricia Marshall
    Patricia Marshall was an American actress and singer best known for her work in mid-20th-century film and musical theatre.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded690f2e08190ad9dad6dc05a164a completed April 15, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe8bda691481909c2d89a362782ed8 completed May 9, 2026, 1:20 a.m.
Created at: April 10, 2026, 2:39 a.m.