Triple

T21738222
Position Surface form Disambiguated ID Type / Status
Subject Tarter E536581 entity
Predicate usedBy P260 FINISHED
Object Jill Tarter 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: Jill Tarter | Statement: [Tarter, usedBy, Jill Tarter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jill Tarter
Context triple: [Tarter, usedBy, Jill Tarter]
  • A. Jill Tarter chosen
    Jill Tarter is an American astronomer best known as a pioneering leader in the scientific search for extraterrestrial intelligence (SETI).
  • B. Suzanne Holman
    Suzanne Holman, later known as Suzanne Farrington, was the daughter of famed actress Vivien Leigh and a British woman who largely lived outside the public spotlight.
  • C. Ann Druyan
    Ann Druyan is an American writer and producer best known for co-writing the original "Cosmos" television series and continuing Carl Sagan’s legacy in popularizing science and astronomy.
  • D. Sandra Jo Tinsley
    Sandra Jo Tinsley is best known as the wife of American actor Forrest Tucker, a popular film and television star active from the 1940s through the 1970s.
  • E. Lisa Ann Walter
    Lisa Ann Walter is an American actress and comedian best known for her roles in films like "The Parent Trap" (1998) and the TV series "Abbott Elementary."
  • 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_69e0c46df5448190b4322127ffc4c690 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69effd0e94c4819096bace0c661f5156 completed April 28, 2026, 12:19 a.m.
Created at: April 16, 2026, 6:49 p.m.