Triple

T13091440
Position Surface form Disambiguated ID Type / Status
Subject Tommy Flowers E310471 entity
Predicate givenName P17 FINISHED
Object Thomas
Thomas is the given first name of Tommy Flowers, the British engineer who designed the Colossus codebreaking computer during World War II.
 E1023332 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 | Statement: [Tommy Flowers, givenName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Thomas
Context triple: [Tommy Flowers, givenName, Thomas]
  • A. Thomas
    Thomas is the full given name of Tom Brady, the legendary NFL quarterback widely regarded as one of the greatest players in American football history.
  • B. Thomas
    Thomas is the formal given name of American politician Tom Daschle, who served as U.S. Senate Majority Leader.
  • C. Thomas
    Thomas is the given name of Sir Stamford Raffles, the British statesman best known as the founder of modern Singapore.
  • D. Thomas
    Thomas is the given name of Thomas Pitt, 1st Baron Camelford, a British naval officer and aristocrat known for his volatile temperament in the late 18th and early 19th centuries.
  • E. Thomas
    Thomas is the formal given name of the fictional crime boss Tommy Shelby from the television series "Peaky Blinders."
  • 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
Triple: [Tommy Flowers, givenName, Thomas]
Generated description
Thomas is the given first name of Tommy Flowers, the British engineer who designed the Colossus codebreaking computer during World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Thomas
Target entity description: Thomas is the given first name of Tommy Flowers, the British engineer who designed the Colossus codebreaking computer during World War II.
  • A. Thomas
    Thomas is the given first name of Tom Harmon, the famed American football player and sportscaster.
  • B. Thomas
    Thomas is the given name of British entertainer Tommy Steele, a pioneering rock and roll singer and actor.
  • C. Thomas
    Thomas is the given name of Thomas Malthus, the influential English economist and demographer known for his theories on population growth and resource limits.
  • D. Thomas
    Thomas is the middle name of the British chemist and scientific adviser Henry Tizard.
  • E. Thomas
    Thomas is the first name of British screenwriter and novelist Nigel Kneale, best known for creating the Quatermass science-fiction series.
  • 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d9813acbac8190b2fe5e07287457cf completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e27058dc8190a64e1a929f296619 completed May 3, 2026, 5:51 a.m.
NEDg Description generation batch_69f6e6a8b15081908d80cd63b0c423f6 completed May 3, 2026, 6:09 a.m.
NED2 Entity disambiguation (via description) batch_69f6e7490cc48190b596338cd3a0fd22 completed May 3, 2026, 6:12 a.m.
Created at: April 9, 2026, 9:03 p.m.