Triple

T12007749
Position Surface form Disambiguated ID Type / Status
Subject John Swinney E285825 entity
Predicate givenName P17 FINISHED
Object John
John Swinney is a Scottish politician who has served as leader of the Scottish National Party and held several senior roles in the Scottish Government.
E963158 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: John | Statement: [John Swinney, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Swinney, givenName, John]
  • A. John
    John is the given name of John J. Pershing, the famed American general who led the American Expeditionary Forces in World War I.
  • B. John
    John Vassall Jr. was a British civil servant who became notorious as a Soviet spy during the Cold War.
  • C. John
    John is the given name of John A. Roebling II, an American civil engineer and philanthropist from the prominent Roebling family associated with major bridge construction.
  • D. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • E. John
    John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
  • 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: John
Triple: [John Swinney, givenName, John]
Generated description
John Swinney is a Scottish politician who has served as leader of the Scottish National Party and held several senior roles in the Scottish Government.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John Swinney is a Scottish politician who has served as leader of the Scottish National Party and held several senior roles in the Scottish Government.
  • A. John
    John Reid, Baron Reid of Cardowan, is a Scottish Labour politician who held several senior UK government posts, including Home Secretary and Defence Secretary, in the late 1990s and 2000s.
  • B. John
    John, known formally as Lord McFall of Alcluith, is a British Labour politician and life peer who has served in prominent parliamentary roles, including as Lord Speaker of the House of Lords.
  • C. John
    John is the given name of John Prescott, a British Labour Party politician who served as Deputy Prime Minister of the United Kingdom from 1997 to 2007.
  • D. John
    John Fetterman is an American politician serving as the junior United States senator from Pennsylvania and former lieutenant governor of the state.
  • E. John
    John is the first name of Canadian politician Jack Layton, a prominent former leader of Canada’s New Democratic Party.
  • 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_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903c5cfc08190821e4b2940c51416 completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f642801881909a94d67c99bfd110 completed May 2, 2026, 1:04 p.m.
NEDg Description generation batch_69f5fde880f4819094b2170bf4e82138 completed May 2, 2026, 1:36 p.m.
NED2 Entity disambiguation (via description) batch_69f5ffc2cfd08190b87eccd3a73afc77 completed May 2, 2026, 1:44 p.m.
Created at: April 8, 2026, 9:46 p.m.