Triple

T5253061
Position Surface form Disambiguated ID Type / Status
Subject Pat Evison E118633 entity
Predicate familyName P18 FINISHED
Object Evison
Evison is a surname most notably associated with New Zealand actress Pat Evison, recognized for her work in film, television, and theatre.
 E506409 NE FINISHED

How this triple was built (4 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: Evison | Statement: [Pat Evison, familyName, Evison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Evison
Context triple: [Pat Evison, familyName, Evison]
  • A. Ewins
    Ewins is a surname variant of Ewing, typically of Scottish or Irish origin.
  • B. Norval
    Norval is a small historic village in Ontario, Canada, known for its scenic Credit River setting and association with author Lucy Maud Montgomery.
  • C. Estey
    Estey is a surname and place name most commonly associated with North American families and locations, sometimes appearing as a variant spelling of similar names like Easty.
  • D. Vacone
    Vacone is a small historic hilltop village in the Lazio region of central Italy, known for its scenic countryside and traditional rural character.
  • E. Earle
    Earle is the middle name of Gordon E. Moore, the co-founder of Intel and originator of Moore’s Law.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Evison
Triple: [Pat Evison, familyName, Evison]
Generated description
Evison is a surname most notably associated with New Zealand actress Pat Evison, recognized for her work in film, television, and theatre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Evison
Target entity description: Evison is a surname most notably associated with New Zealand actress Pat Evison, recognized for her work in film, television, and theatre.
  • A. Ewins
    Ewins is a surname variant of Ewing, typically of Scottish or Irish origin.
  • B. Norval
    Norval is a small historic village in Ontario, Canada, known for its scenic Credit River setting and association with author Lucy Maud Montgomery.
  • C. Estey
    Estey is a surname and place name most commonly associated with North American families and locations, sometimes appearing as a variant spelling of similar names like Easty.
  • D. Vacone
    Vacone is a small historic hilltop village in the Lazio region of central Italy, known for its scenic countryside and traditional rural character.
  • E. Earle
    Earle is the middle name of Gordon E. Moore, the co-founder of Intel and originator of Moore’s Law.
  • F. None of above. chosen

Provenance (5 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_69bd446978108190bb5f9c5c23d93f88 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b7cd7f4819098e591df07564a52 completed March 20, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69befe72c91c8190ab0f988dca420399 completed March 21, 2026, 8:24 p.m.
NEDg Description generation batch_69beff668dbc8190bc71c8dae2b5ca72 completed March 21, 2026, 8:28 p.m.
NED2 Entity disambiguation (via description) batch_69bf00120fe88190817badb72977566e completed March 21, 2026, 8:31 p.m.
Created at: March 20, 2026, 1:50 p.m.