Triple

T347670
Position Surface form Disambiguated ID Type / Status
Subject Samuel Langhorne Clemens E6975 entity
Predicate hasPseudonym P3799 FINISHED
Object Thomas Jefferson Snodgrass
Thomas Jefferson Snodgrass is an early, lesser-known pseudonym used by American writer Samuel Langhorne Clemens, better known as Mark Twain.
E154120 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: Thomas Jefferson Snodgrass | Statement: [Samuel Langhorne Clemens, hasPseudonym, Thomas Jefferson Snodgrass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Jefferson Snodgrass
Context triple: [Samuel Langhorne Clemens, hasPseudonym, Thomas Jefferson Snodgrass]
  • A. John Dandridge
    John Dandridge was a Virginia planter and colonial official best known as the father of Martha Washington, the first First Lady of the United States.
  • B. Charles Steele Jr.
    Charles Steele Jr. is an American civil rights leader and politician best known for his longtime leadership of the Southern Christian Leadership Conference, the historic organization once led by Martin Luther King Jr.
  • C. James Edward Rice
    James Edward Rice, better known as Jim Rice, is a former Major League Baseball left fielder who spent his entire career with the Boston Red Sox and was inducted into the Baseball Hall of Fame.
  • D. John A. Wilson
    John A. Wilson was a prominent Washington, D.C. politician and public servant, notably serving as chairman of the Council of the District of Columbia.
  • E. Christopher Weaver
    Christopher Weaver is an American entrepreneur and video game industry pioneer best known as the founder of ZeniMax Media, the parent company of Bethesda Softworks.
  • 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: Thomas Jefferson Snodgrass
Triple: [Samuel Langhorne Clemens, hasPseudonym, Thomas Jefferson Snodgrass]
Generated description
Thomas Jefferson Snodgrass is an early, lesser-known pseudonym used by American writer Samuel Langhorne Clemens, better known as Mark Twain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thomas Jefferson Snodgrass
Target entity description: Thomas Jefferson Snodgrass is an early, lesser-known pseudonym used by American writer Samuel Langhorne Clemens, better known as Mark Twain.
  • A. John Dandridge
    John Dandridge was a Virginia planter and colonial official best known as the father of Martha Washington, the first First Lady of the United States.
  • B. Charles Steele Jr.
    Charles Steele Jr. is an American civil rights leader and politician best known for his longtime leadership of the Southern Christian Leadership Conference, the historic organization once led by Martin Luther King Jr.
  • C. James Edward Rice
    James Edward Rice, better known as Jim Rice, is a former Major League Baseball left fielder who spent his entire career with the Boston Red Sox and was inducted into the Baseball Hall of Fame.
  • D. John A. Wilson
    John A. Wilson was a prominent Washington, D.C. politician and public servant, notably serving as chairman of the Council of the District of Columbia.
  • E. Christopher Weaver
    Christopher Weaver is an American entrepreneur and video game industry pioneer best known as the founder of ZeniMax Media, the parent company of Bethesda Softworks.
  • 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_69a2e7951ba08190960e90823b5078f3 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2ee043fac8190af72291c04761687 completed Feb. 28, 2026, 1:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69acc5e4ba188190876eea46a4f6ec1c completed March 8, 2026, 12:42 a.m.
NEDg Description generation batch_69acc6dbd80881908d640ee204ce9a12 completed March 8, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69acc8199f508190a86c18ad9085d341 completed March 8, 2026, 12:51 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.