Triple

T14276275
Position Surface form Disambiguated ID Type / Status
Subject Borusa E353923 entity
Predicate portrayedBy P1507 FINISHED
Object Angus MacKay
Angus MacKay was a British character actor best known to science fiction fans for his roles in the classic Doctor Who television series.
E1100156 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: Angus MacKay | Statement: [Borusa, portrayedBy, Angus MacKay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angus MacKay
Context triple: [Borusa, portrayedBy, Angus MacKay]
  • A. Angus Sutherland
    Angus Sutherland is a Canadian actor and producer, known both for his work in film and television and as a member of the Sutherland acting family.
  • B. Angus McGill
    Angus McGill was a British journalist and humorist known for his witty newspaper columns and light comic writing.
  • C. Duncan MacRae
    Duncan MacRae is a notable individual distinguished by achievements significant enough to be historically or culturally recognized under the surname MacRae.
  • D. Malcolm MacLeod
    Malcolm MacLeod was a Scottish crofter from the Isle of Lewis and the father of Mary Anne MacLeod, who later became the mother of Donald Trump.
  • E. Malcolm MacRury
    Malcolm MacRury is a Canadian television writer and producer known for his work on series such as Republic of Doyle and other acclaimed dramas.
  • 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: Angus MacKay
Triple: [Borusa, portrayedBy, Angus MacKay]
Generated description
Angus MacKay was a British character actor best known to science fiction fans for his roles in the classic Doctor Who television series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Angus MacKay
Target entity description: Angus MacKay was a British character actor best known to science fiction fans for his roles in the classic Doctor Who television series.
  • A. Angus Sutherland
    Angus Sutherland is a Canadian actor and producer, known both for his work in film and television and as a member of the Sutherland acting family.
  • B. Angus McGill
    Angus McGill was a British journalist and humorist known for his witty newspaper columns and light comic writing.
  • C. Duncan MacRae
    Duncan MacRae is a notable individual distinguished by achievements significant enough to be historically or culturally recognized under the surname MacRae.
  • D. Malcolm MacLeod
    Malcolm MacLeod was a Scottish crofter from the Isle of Lewis and the father of Mary Anne MacLeod, who later became the mother of Donald Trump.
  • E. Malcolm MacRury
    Malcolm MacRury is a Canadian television writer and producer known for his work on series such as Republic of Doyle and other acclaimed dramas.
  • 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_69d8278d25148190abf1a8c8f5f533ad completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6583f0ec81909ebfc7a2c6351ff8 completed April 14, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd647b37a8819095fe0bb62e0373fb completed May 8, 2026, 4:20 a.m.
NEDg Description generation batch_69fd6539793881909d1fd3985c171837 completed May 8, 2026, 4:23 a.m.
NED2 Entity disambiguation (via description) batch_69fd65c06fc88190a7d2a84d7858b20f completed May 8, 2026, 4:25 a.m.
Created at: April 10, 2026, 1:10 a.m.