Triple

T19105812
Position Surface form Disambiguated ID Type / Status
Subject John Johnston Duddy E467650 entity
Predicate middleName P143 FINISHED
Object Johnston 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: Johnston | Statement: [John Johnston Duddy, middleName, Johnston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johnston
Context triple: [John Johnston Duddy, middleName, Johnston]
  • A. Johnston chosen
    Johnston is a surname and given name of Scottish and Irish origin, commonly used as a variant of Johnson.
  • B. Johnston
    Johnston is a suburban town in Providence County, Rhode Island, known for hosting several state government facilities and a mix of residential and commercial areas.
  • C. Johnston
    Johnston is a suburban city in central Iowa, United States, known for hosting the headquarters of the Iowa National Guard and several major corporate offices.
  • D. Johnston
    Johnston is a residential suburb located within the greater Darwin metropolitan region in Australia's Northern Territory.
  • E. New Johnston
    New Johnston is a modernized sans-serif typeface developed as an updated version of the original Johnston design used for London’s public transport system.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e37159688190a6896d9730214ba8 completed April 20, 2026, 8:27 a.m.
Created at: April 10, 2026, 12:04 p.m.