Triple

T16818468
Position Surface form Disambiguated ID Type / Status
Subject Lord George Germain E408816 entity
Predicate givenName P17 FINISHED
Object George
George is the given name of Lord George Germain, an 18th-century British statesman and military leader involved in the administration of the American Revolutionary War.
E1234981 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: [Lord George Germain, givenName, George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George
Context triple: [Lord George Germain, givenName, George]
  • A. George
    George is a common English surname of likely Greek and Latin origin, associated with numerous notable historical and contemporary figures.
  • B. George
    George is the given name of George Murray, 6th Duke of Atholl, a Scottish peer and nobleman of the 19th century.
  • C. 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.
  • D. George
    George is the given first name of the American gangster Bugs Moran, a prominent Prohibition-era mobster in Chicago.
  • E. George
    George is the given name of George North, 3rd Earl of Guilford, a British peer from the late 18th and early 19th centuries.
  • 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: [Lord George Germain, givenName, George]
Generated description
George is the given name of Lord George Germain, an 18th-century British statesman and military leader involved in the administration of the American Revolutionary War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: George
Target entity description: George is the given name of Lord George Germain, an 18th-century British statesman and military leader involved in the administration of the American Revolutionary War.
  • A. George
    George is the given name of Lord George Murray, a prominent Scottish Jacobite general during the 18th-century uprisings.
  • B. George
    George is the given name of George Spencer, 4th Duke of Marlborough, an 18th-century British nobleman and politician.
  • C. George
    George is the given name of George Goring, Lord Goring, a prominent Royalist commander during the English Civil War.
  • D. George
    George is the given name of George Brydges Rodney, an 18th-century British naval officer and admiral noted for his victories during the American Revolutionary War.
  • E. George
    George is the given name of George Montagu-Dunk, 2nd Earl of Halifax, an influential 18th-century British statesman and colonial administrator.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b2e476d48190bff097055cc353dc completed April 18, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b28592c08190855a7fa5b0a350f5 completed May 10, 2026, 4:29 p.m.
NEDg Description generation batch_6a00b399786c8190acbd188ab55b1fa0 completed May 10, 2026, 4:34 p.m.
NED2 Entity disambiguation (via description) batch_6a00b466ecd08190b7b5ee54476631ab completed May 10, 2026, 4:37 p.m.
Created at: April 10, 2026, 5:23 a.m.