Triple

T2627945
Position Surface form Disambiguated ID Type / Status
Subject John Russell, 4th Earl Russell E59164 entity
Predicate givenName P17 FINISHED
Object John
John is the given name of John Russell, 4th Earl Russell, a British peer and politician.
E285990 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 Russell, 4th Earl Russell, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Russell, 4th Earl Russell, givenName, John]
  • A. John
    John is traditionally regarded as the author of the New Testament’s Book of Revelation, a prophetic and apocalyptic text in Christian scripture.
  • B. John
    John is the given name of John Perry Barlow, the American poet, essayist, and co-founder of the Electronic Frontier Foundation known for his advocacy of digital rights.
  • C. John
    John is the given name of the renowned British mathematician John H. Conway, known for his work in group theory, number theory, and the invention of the Game of Life.
  • D. John
    John is the given name of John Nance Garner, who served as the 32nd vice president of the United States under President Franklin D. Roosevelt.
  • E. John
    John is the given name of John F. Sattler, likely referring to him in a more informal or abbreviated context.
  • 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 Russell, 4th Earl Russell, givenName, John]
Generated description
John is the given name of John Russell, 4th Earl Russell, a British peer and politician.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is the given name of John Russell, 4th Earl Russell, a British peer and politician.
  • A. John
    John is the given name of John Russell, 1st Earl Russell, a prominent 19th-century British statesman and Prime Minister.
  • B. John
    John is the given name of John Russell, Viscount Amberley, a 19th-century British politician and the father of philosopher Bertrand Russell.
  • C. John
    John is the given name of John Winston Spencer-Churchill, the 7th Duke of Marlborough, a prominent 19th-century British aristocrat and politician.
  • D. John
    John is the given name of Sir John Anderson, a British civil servant and politician who played a key role in government during the early 20th century.
  • E. John
    John is the given name of Sir John Trevor, a historical British political figure.
  • 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_69ab4ac558388190962492cd2e1b0ce6 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8c2e3d88190a972f58356f282cc completed March 7, 2026, 7:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69af98b50fa08190abe65b53081cb06b completed March 10, 2026, 4:06 a.m.
NEDg Description generation batch_69af999d0b848190afcd7b27daa024e1 completed March 10, 2026, 4:10 a.m.
NED2 Entity disambiguation (via description) batch_69af9a48b2588190addeef916b0afef2 completed March 10, 2026, 4:12 a.m.
Created at: March 6, 2026, 9:50 p.m.