Triple

T21419350
Position Surface form Disambiguated ID Type / Status
Subject John Hornsby E528392 entity
Predicate familyName P18 FINISHED
Object Hornsby 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: Hornsby | Statement: [John Hornsby, familyName, Hornsby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hornsby
Context triple: [John Hornsby, familyName, Hornsby]
  • A. Hornsby
    Hornsby is a major residential and commercial suburb in northern Sydney, New South Wales, known for its busy shopping precinct and transport hub.
  • B. Hornsby chosen
    Hornsby is a surname most famously associated with Rogers Hornsby, one of Major League Baseball’s greatest hitters.
  • C. Kurrajong
    Kurrajong is a locality in the Australian Capital Territory known for its rural character and proximity to the Ginninderra region.
  • D. Kurrajong
    Kurrajong is an electorate of the Australian Capital Territory Legislative Assembly that covers central Canberra and surrounding suburbs.
  • E. Kingsgrove
    Kingsgrove is a residential suburb in southern Sydney, New South Wales, Australia, known for its family-friendly streets, local shopping areas, and convenient rail access to the city.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b2ccddc08190b4f66fa6ccda41e2 completed April 22, 2026, 11:36 a.m.
Created at: April 16, 2026, 5:47 p.m.