Triple

T4066275
Position Surface form Disambiguated ID Type / Status
Subject Thomson E86329 entity
Predicate hasNotableBearer P458 FINISHED
Object John Edgar Thomson
John Edgar Thomson was a prominent 19th-century American civil engineer and railroad executive who served as the influential president of the Pennsylvania Railroad.
E410488 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 Edgar Thomson | Statement: [Thomson, hasNotableBearer, John Edgar Thomson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Edgar Thomson
Context triple: [Thomson, hasNotableBearer, John Edgar Thomson]
  • A. Clarence A. Crane
    Clarence A. Crane was an American businessman best known as the inventor of Life Savers candy.
  • B. Edward Nichols
    Edward Nichols was a physicist best known for founding the influential scientific journal Physical Review.
  • C. William Tracy
    William Tracy was an American film actor best known for his comedic roles in 1930s and 1940s Hollywood movies.
  • D. Alfred B. Mullett
    Alfred B. Mullett was a prominent 19th-century American architect who served as Supervising Architect of the U.S. Treasury and designed numerous notable federal buildings in the Second Empire style.
  • E. Thomas Whitehurst
    Thomas Whitehurst was an educator and mentor known for teaching and influencing the English clockmaker and scientist John Whitehurst.
  • 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 Edgar Thomson
Triple: [Thomson, hasNotableBearer, John Edgar Thomson]
Generated description
John Edgar Thomson was a prominent 19th-century American civil engineer and railroad executive who served as the influential president of the Pennsylvania Railroad.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Edgar Thomson
Target entity description: John Edgar Thomson was a prominent 19th-century American civil engineer and railroad executive who served as the influential president of the Pennsylvania Railroad.
  • A. Clarence A. Crane
    Clarence A. Crane was an American businessman best known as the inventor of Life Savers candy.
  • B. Edward Nichols
    Edward Nichols was a physicist best known for founding the influential scientific journal Physical Review.
  • C. William Tracy
    William Tracy was an American film actor best known for his comedic roles in 1930s and 1940s Hollywood movies.
  • D. Alfred B. Mullett
    Alfred B. Mullett was a prominent 19th-century American architect who served as Supervising Architect of the U.S. Treasury and designed numerous notable federal buildings in the Second Empire style.
  • E. Thomas Whitehurst
    Thomas Whitehurst was an educator and mentor known for teaching and influencing the English clockmaker and scientist John Whitehurst.
  • 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_69aed93c69208190a4efac0efe3cd69b completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbf58d9c8190936e453b0d397cb0 completed March 9, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562b17c888190ac4771f2bb4f0d58 completed March 14, 2026, 1:29 p.m.
NEDg Description generation batch_69b5637e72948190989169b0a46916a8 completed March 14, 2026, 1:32 p.m.
NED2 Entity disambiguation (via description) batch_69b563fc4cb081908ba0f1a799338a8c completed March 14, 2026, 1:34 p.m.
Created at: March 9, 2026, 3:38 p.m.