Triple

T20273485
Position Surface form Disambiguated ID Type / Status
Subject Eve Alda E502949 entity
Predicate sibling P363 FINISHED
Object Elizabeth Alda 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: Elizabeth Alda | Statement: [Eve Alda, sibling, Elizabeth Alda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Alda
Context triple: [Eve Alda, sibling, Elizabeth Alda]
  • A. Elizabeth Alda chosen
    Elizabeth Alda is an American actress, best known for her role in the film "The Four Seasons" and as the daughter of actor and director Alan Alda.
  • B. Alma Garret
    Alma Garret is a wealthy, opium-addicted widow and prominent businesswoman in the frontier town of Deadwood in the television series "Deadwood."
  • C. Rosita Douglas
    Rosita Douglas is a Swedish-born aristocrat and former model best known as the first wife of John George Vanderbilt Henry Spencer-Churchill, the 11th Duke of Marlborough.
  • D. Anne Alvaro
    Anne Alvaro is a French actress acclaimed for her work in film, theatre, and television, noted for her nuanced character roles and multiple prestigious awards.
  • E. Barbara Luna
    Barbara Luna is an American actress known for her numerous film and television roles from the 1950s onward, including appearances in productions such as the historical drama "Che!" and the original "Star Trek" series.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e675e104f081909d17c1963a5db528 completed April 20, 2026, 6:52 p.m.
Created at: April 16, 2026, 10:28 a.m.