Triple

T6627909
Position Surface form Disambiguated ID Type / Status
Subject Arrow E149849 entity
Predicate starring P1507 FINISHED
Object Susanna Thompson E378185 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: Susanna Thompson | Statement: [Arrow, starring, Susanna Thompson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susanna Thompson
Context triple: [Arrow, starring, Susanna Thompson]
  • A. Susanna Thompson chosen
    Susanna Thompson is an American actress known for her work in film and television, including prominent roles in series like "Arrow" and "Star Trek: Voyager."
  • B. Susanna Nelson
    Susanna Nelson was a daughter of Edmund Nelson, the Anglican clergyman best known as the father of Admiral Horatio Nelson.
  • C. Nell Thompson
    Nell Thompson was the wife of American aviator and military leader Claire Lee Chennault, associated with his career and life during the World War II era.
  • D. Sue Ann Thompson
    Sue Ann Thompson is an American advocate and former First Lady of Wisconsin, known for her work in women's health and as the longtime wife of politician Tommy Thompson.
  • E. Susannah Martin
    Susannah Martin was a Massachusetts woman executed for alleged witchcraft in 1692, remembered as one of the victims of the Salem witch trials.
  • 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_69c687ee50048190aa151765bef16193 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6afa2e4a48190ba3c70013bab14f2 completed March 27, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723b575a08190a3e0b1f233c36ba0 completed March 28, 2026, 12:41 a.m.
Created at: March 27, 2026, 1:59 p.m.