Triple

T17684483
Position Surface form Disambiguated ID Type / Status
Subject John A. Dix E440851 entity
Predicate familyName P18 FINISHED
Object Dix 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: Dix | Statement: [John A. Dix, familyName, Dix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dix
Context triple: [John A. Dix, familyName, Dix]
  • A. Dix chosen
    Dix is the surname of Dorothea Dix, the 19th-century American social reformer known for her pioneering work in mental health care and prison reform.
  • B. Dixon
    Dixon is an alternative name for Dikson, a remote Arctic settlement and port in northern Russia.
  • C. Dixon
    Dixon is a small agricultural city in Northern California known historically for sheep ranching and its annual May Fair.
  • D. Villard
    Villard is a surname most notably associated with Oswald Garrison Villard, an American journalist and civil rights activist.
  • E. Villard
    Villard is a small locality in the Haut-Chablais area of the French Alps, known for its mountainous setting and proximity to outdoor recreation.
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4704710488190826aaf0bdd4b2088 completed April 19, 2026, 6:03 a.m.
Created at: April 10, 2026, 10:02 a.m.