Triple

T19184288
Position Surface form Disambiguated ID Type / Status
Subject Anna Roosevelt E469658 entity
Predicate givenName P17 FINISHED
Object Anna 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: Anna | Statement: [Anna Roosevelt, givenName, Anna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna
Context triple: [Anna Roosevelt, givenName, Anna]
  • A. Anna chosen
    Anna is the given name of Anna Murray Douglass, an African American abolitionist and the first wife of Frederick Douglass.
  • B. Anna
    Anna is a small city in north-central Texas that forms part of the fast-growing suburban region north of Dallas.
  • C. Anna
    Anna is the given first name of the American actress, comedian, and director Nancy Walker.
  • D. Anna
    Anna was a medieval Rus' princess from Novgorod, known as the daughter of Mstislav I of Kiev and a member of the Rurikid dynasty.
  • E. Anna
    Anna is a fictional character from the novel and film "How to Make an American Quilt," one of the women whose life stories are woven into the narrative of a quilting circle.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f61f1d9c8190b67555383d821958 completed April 20, 2026, 9:47 a.m.
Created at: April 10, 2026, 12:07 p.m.