Triple

T22607696
Position Surface form Disambiguated ID Type / Status
Subject Sue Bayliss E566604 entity
Predicate neighborOf P350 FINISHED
Object Keller family 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: Keller family | Statement: [Sue Bayliss, neighborOf, Keller family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keller family
Context triple: [Sue Bayliss, neighborOf, Keller family]
  • A. Keller family chosen
    The Keller family is an American family best known as the childhood family of Helen Keller, whose historic home Ivy Green in Tuscumbia, Alabama, is preserved as a museum.
  • B. Kennerly family
    The Kennerly family is a historically notable American family known through members such as Harriet Kennerly Radford, who were active in early U.S. social and political life.
  • C. Kolb family
    The Kolb family was a Southern landowning family historically associated with the Kolb Farm in Georgia, notable for its role during the American Civil War.
  • D. Kimball family
    The Kimball family is a benefactor family recognized for its significant philanthropic contributions to institutions such as the Kimball Natural History Museum.
  • E. Hauser family
    The Hauser family is a philanthropic family known for its significant support of legal education and global academic initiatives, particularly at New York University School of Law.
  • 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_69e245884860819081046ce07d5872c4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f167e75658819089153eab7563540c completed April 29, 2026, 2:07 a.m.
Created at: April 17, 2026, 2:55 p.m.