Triple

T17861665
Position Surface form Disambiguated ID Type / Status
Subject John Manners, Marquess of Granby E446085 entity
Predicate givenName P17 FINISHED
Object John
John Manners, Marquess of Granby, was an 18th-century British soldier and popular military leader renowned for his service in the Seven Years' War and his enduring legacy in English pub names.
E1292363 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 Manners, Marquess of Granby, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Manners, Marquess of Granby, givenName, John]
  • A. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • B. John
    John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
  • C. John
    John is the given first name of the 19th-century English theologian and social reformer Frederick Denison Maurice.
  • D. John
    John is the given name of John Eales, the renowned former Australian rugby union captain and World Cup winner.
  • E. John
    John is the given name of the English jurist and scholar John Selden, a prominent 17th-century authority on law and constitutional history.
  • 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 Manners, Marquess of Granby, givenName, John]
Generated description
John Manners, Marquess of Granby, was an 18th-century British soldier and popular military leader renowned for his service in the Seven Years' War and his enduring legacy in English pub names.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John Manners, Marquess of Granby, was an 18th-century British soldier and popular military leader renowned for his service in the Seven Years' War and his enduring legacy in English pub names.
  • A. John
    John is the given name of Sir John Moore, the renowned British Army general noted for his leadership during the Napoleonic Wars.
  • B. John
    John is the given name of John Churchill, 1st Duke of Marlborough, the renowned English general and statesman of the late 17th and early 18th centuries.
  • C. John
    John is the given name of Sir John Borlase Warren, a prominent British naval officer and politician of the late 18th and early 19th centuries.
  • D. John
    John is the given name of John Campbell, 5th Duke of Argyll, a prominent 18th-century Scottish nobleman and military leader.
  • E. John
    John is the given name of John Campbell, 2nd Duke of Argyll, a prominent Scottish nobleman and military leader of the early 18th century.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e49790ea148190b7a966812d44f430 completed April 19, 2026, 8:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a030c5e368081908df3a20cd40aeb9f completed May 12, 2026, 11:17 a.m.
NEDg Description generation batch_6a030d2ebb44819083c58cfae6c7ca47 completed May 12, 2026, 11:21 a.m.
NED2 Entity disambiguation (via description) batch_6a030e1b78388190bbad5f4f967c31d3 completed May 12, 2026, 11:25 a.m.
Created at: April 10, 2026, 10:17 a.m.