Triple

T20197847
Position Surface form Disambiguated ID Type / Status
Subject George Washington Custis Lee E493134 entity
Predicate givenName P17 FINISHED
Object George
George is the given name of George Washington Custis Lee, a Confederate general and the eldest son of Robert E. Lee.
E1419207 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 Washington Custis Lee, givenName, George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George
Context triple: [George Washington Custis Lee, givenName, George]
  • A. George
    George is the given first name of the fictional character Gob Bluth from the television series "Arrested Development."
  • B. George
    George is the middle name of William George Barker, a renowned Canadian World War I flying ace and Victoria Cross recipient.
  • C. George
    George is the given name of George Stanley, 9th Baron Strange, an English nobleman and politician of the late 15th century.
  • D. George
    George is the given name of George Carnegie, 6th Earl of Northesk, a Scottish nobleman and naval officer in the Royal Navy.
  • E. George
    George is the given name of Lord George Murray, a prominent Scottish Jacobite general during the 18th-century uprisings.
  • 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 Washington Custis Lee, givenName, George]
Generated description
George is the given name of George Washington Custis Lee, a Confederate general and the eldest son of Robert E. Lee.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: George
Target entity description: George is the given name of George Washington Custis Lee, a Confederate general and the eldest son of Robert E. Lee.
  • A. George
    George is the given name of George Patton IV, a U.S. Army general and son of the famed World War II General George S. Patton.
  • B. George
    George is the given name of George Armstrong Custer, the controversial U.S. Army officer and cavalry commander best known for his defeat and death at the Battle of the Little Bighorn.
  • C. George
    George is the given name of George Rogers Clark Todd, a 19th-century American physician and Confederate surgeon during the Civil War.
  • D. George
    George is the first name of George Washington, the first President of the United States and a key leader in the American Revolutionary War.
  • E. 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.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66d8afe408190a7a9202ed67698e6 completed April 20, 2026, 6:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a084b7e51888190bf36b6cf8d68a556 completed May 16, 2026, 10:48 a.m.
NEDg Description generation batch_6a084c17a0808190a6ea7ea52246be8b completed May 16, 2026, 10:51 a.m.
NED2 Entity disambiguation (via description) batch_6a084cf11ff8819086138489b9645c75 completed May 16, 2026, 10:54 a.m.
Created at: April 11, 2026, 11:37 p.m.