Triple

T6405940
Position Surface form Disambiguated ID Type / Status
Subject John Meurig Thomas E127577 entity
Predicate familyName P18 FINISHED
Object Thomas
Thomas is a common Welsh and English surname borne by numerous notable individuals across fields such as science, politics, sports, and the arts.
E251923 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: [John Meurig Thomas, familyName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas
Context triple: [John Meurig Thomas, familyName, Thomas]
  • A. Thomas
    Thomas is the middle name of Edward Thomas Wailes, an American diplomat.
  • B. Thomas
    Thomas is the given first name of the renowned American playwright Tennessee Williams, known for works such as "A Streetcar Named Desire" and "Cat on a Hot Tin Roof."
  • C. Thomas
    Thomas is the middle name of William T. Sampson, a notable U.S. Navy admiral from the Spanish–American War era.
  • D. Thomas
    Thomas is the given first name of American astronaut Ken Mattingly, known for his role in the Apollo and Space Shuttle programs.
  • E. Thomas
    Thomas is the given name of Sir Thomas Blamey, an Australian field marshal and senior military commander during World War II.
  • 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: [John Meurig Thomas, familyName, Thomas]
Generated description
Thomas is a common Welsh and English surname borne by numerous notable individuals across fields such as science, politics, sports, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thomas
Target entity description: Thomas is a common Welsh and English surname borne by numerous notable individuals across fields such as science, politics, sports, and the arts.
  • A. Thomas chosen
    Thomas is a common surname of English and Welsh origin, derived from the given name Thomas and borne by numerous notable individuals worldwide.
  • B. Thomas
    Thomas is a common masculine given name of Aramaic origin, widely used in English-speaking and many other cultures.
  • 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 given name of Thomas Paine, the influential 18th-century political philosopher and writer known for works like "Common Sense" and "The Rights of Man."
  • E. Thomas
    Thomas is the given name of Thomas Osborne, 1st Duke of Leeds, a prominent 17th-century English statesman and politician.
  • F. None of above.

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_69c0083723d88190b1e37b19df162c08 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c068b22c74819092228010708aec6b completed March 22, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64ba5b0bc8190aefa07c77c99be83 completed March 27, 2026, 9:19 a.m.
NEDg Description generation batch_69c64f37cfa88190a1b896d1893a28d4 completed March 27, 2026, 9:34 a.m.
NED2 Entity disambiguation (via description) batch_69c64fa0196c8190aa4c7241acf0c0b6 completed March 27, 2026, 9:36 a.m.
Created at: March 22, 2026, 4:41 p.m.