Triple

T10542292
Position Surface form Disambiguated ID Type / Status
Subject George Spencer, 4th Duke of Marlborough E248726 entity
Predicate givenName P17 FINISHED
Object George
George is the given name of George Spencer, 4th Duke of Marlborough, an 18th-century British nobleman and politician.
 E871043 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: George | Statement: [George Spencer, 4th Duke of Marlborough, givenName, George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: George
Context triple: [George Spencer, 4th Duke of Marlborough, givenName, George]
  • A. George
    George is the heroic protagonist of the fantasy film "The Magic Sword," known for embarking on a perilous quest to rescue a princess from an evil sorcerer.
  • B. George
    George is a common English surname of likely Greek and Latin origin, associated with numerous notable historical and contemporary figures.
  • C. George
    George is the given name of George Murray, 6th Duke of Atholl, a Scottish peer and nobleman of the 19th century.
  • D. George
    George is the given name of George de Hevesy, the Hungarian radiochemist and Nobel laureate known for pioneering the use of radioactive tracers in studying chemical processes.
  • E. George
    George is a supporting character in the romantic comedy film "27 Dresses," serving as a colleague and love interest within the story’s central wedding-planning world.
  • 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: George
Triple: [George Spencer, 4th Duke of Marlborough, givenName, George]
Generated description
George is the given name of George Spencer, 4th Duke of Marlborough, an 18th-century British nobleman and politician.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: George
Target entity description: George is the given name of George Spencer, 4th Duke of Marlborough, an 18th-century British nobleman and politician.
  • A. George
    George is the given name of George Spencer-Churchill, 6th Duke of Marlborough, a British aristocrat and politician of the 19th century.
  • B. George
    George is the given name of George Montagu-Dunk, 2nd Earl of Halifax, an influential 18th-century British statesman and colonial administrator.
  • C. George
    George is the given name of Sir George Grey, a prominent 19th-century British colonial governor and statesman.
  • D. George
    George is the given name of Lord George Cavendish, a British aristocrat and politician from the prominent Cavendish family.
  • E. George
    George is the given name of George Monck, 1st Duke of Albemarle, a key English soldier and statesman who helped restore Charles II to the throne in 1660.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5190f46d08190a92b1191881ffb92 completed April 7, 2026, 2:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d933fffc4c81908798094f72a06d18 completed April 10, 2026, 5:31 p.m.
NEDg Description generation batch_69d93802a4488190aa86ae209650d4e7 completed April 10, 2026, 5:48 p.m.
NED2 Entity disambiguation (via description) batch_69d938fcc3c48190a4acaaf75c1aa304 completed April 10, 2026, 5:53 p.m.
Created at: April 6, 2026, 12:32 p.m.