Triple

T21294780
Position Surface form Disambiguated ID Type / Status
Subject John Sparkman E524891 entity
Predicate givenName P17 FINISHED
Object John
John is the given name of John Sparkman, an American politician who served as a U.S. senator from Alabama and was the Democratic vice-presidential nominee in 1952.
E1476320 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 Sparkman, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Sparkman, givenName, John]
  • A. John
    John is the given name of Saint John of Capistrano, a 15th-century Franciscan friar renowned as a preacher, theologian, and leader in the defense of Belgrade.
  • B. John
    John B. Magruder was a Confederate major general during the American Civil War, known for his leadership in the Peninsula Campaign and his flamboyant personality.
  • C. John
    John is the given name of John Bercow, a British politician who served as Speaker of the House of Commons in the UK Parliament.
  • D. John
    John is the given name of the English Romantic poet and nobleman John Byron, 7th Baron Byron.
  • E. John
    John Sirica was a U.S. federal judge best known for presiding over the Watergate scandal trials in the 1970s.
  • 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 Sparkman, givenName, John]
Generated description
John is the given name of John Sparkman, an American politician who served as a U.S. senator from Alabama and was the Democratic vice-presidential nominee in 1952.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is the given name of John Sparkman, an American politician who served as a U.S. senator from Alabama and was the Democratic vice-presidential nominee in 1952.
  • A. John
    John is the given name of John L. McClellan, a long-serving U.S. Senator from Arkansas known for his influential role in mid-20th-century American politics.
  • B. John
    John is the given name of John C. Stennis, a long-serving U.S. Senator from Mississippi known for his influence on defense policy.
  • C. John
    John is the given name of John Sherman Cooper, a prominent American politician and long-serving U.S. Senator from Kentucky.
  • D. John
    John is the given name of John McCain III, the American politician and longtime U.S. senator from Arizona who was the 2008 Republican presidential nominee.
  • E. John
    John is the given name of John Conyers, a long-serving American politician who represented Michigan in the U.S. House of Representatives.
  • 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_69e0b517e6748190850d6f6ddf323d69 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73857784881908c3b8418a4c00c1e completed April 21, 2026, 8:41 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0997f6a5908190958598492a1363e8 completed May 17, 2026, 10:27 a.m.
NEDg Description generation batch_6a0998a3326481908a4dfddfb7b2ecd9 completed May 17, 2026, 10:29 a.m.
NED2 Entity disambiguation (via description) batch_6a09996c8d7c81908cc9874f6e1a3fff completed May 17, 2026, 10:33 a.m.
Created at: April 16, 2026, 4:04 p.m.