Triple

T17837367
Position Surface form Disambiguated ID Type / Status
Subject Richard Arlen E445424 entity
Predicate spouse P13 FINISHED
Object Jobyna Ralston 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: Jobyna Ralston | Statement: [Richard Arlen, spouse, Jobyna Ralston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jobyna Ralston
Context triple: [Richard Arlen, spouse, Jobyna Ralston]
  • A. Jobyna Ralston chosen
    Jobyna Ralston was an American silent film actress best known as Harold Lloyd’s leading lady in several popular 1920s comedies.
  • B. Mary Frances Reynolds
    Mary Frances Reynolds, better known as Debbie Reynolds, was an American actress, singer, and dancer famed for her roles in classic Hollywood films such as "Singin' in the Rain."
  • C. Elizabeth McCord
    Elizabeth McCord is the principled and pragmatic U.S. Secretary of State at the center of the political drama series "Madam Secretary," known for her diplomatic skill and moral conviction.
  • D. Jeanette Hutchinson
    Jeanette Hutchinson is an actress known for her role in the classic British television police drama "Dixon of Dock Green."
  • E. Marie H. Reed
    Marie H. Reed was a community leader and educator in Washington, D.C., recognized for her contributions to local education and civic life.
  • 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_69d8b9f1a6d881909f024bc603111cdb completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48d28c14881909033abd09bbdb135 completed April 19, 2026, 8:07 a.m.
Created at: April 10, 2026, 10:16 a.m.