Triple

T10737141
Position Surface form Disambiguated ID Type / Status
Subject Tamsin E253222 entity
Predicate relatedName P3889 FINISHED
Object Thomas
Thomas is a given name of Aramaic origin commonly used in many English-speaking and European countries.
 E67625 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: [Tamsin, relatedName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Thomas
Context triple: [Tamsin, relatedName, Thomas]
  • A. John
    John is a masculine given name of Hebrew origin, widely used in English-speaking countries and borne by numerous historical and contemporary figures.
  • B. John
    John is the nickname of John Riggins, a former American football running back best known for his Hall of Fame career with the Washington Redskins in the NFL.
  • C. John
    John is the given name of John Adams, the prominent American minimalist and post-minimalist composer known for works like "Nixon in China" and "Short Ride in a Fast Machine."
  • D. John
    John is the given name of actor John Cho, a Korean American performer known for roles in the "Harold & Kumar" films and the "Star Trek" reboot series.
  • E. John
    John is the first name of the fictional character John Connor, the prophesied leader of the human resistance in the Terminator franchise.
  • 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: [Tamsin, relatedName, Thomas]
Generated description
Thomas is a given name of Aramaic origin commonly used in many English-speaking and European countries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Thomas
Target entity description: Thomas is a given name of Aramaic origin commonly used in many English-speaking and European countries.
  • A. Thomas chosen
    Thomas is a common masculine given name of Aramaic origin, widely used in English-speaking and many other cultures.
  • B. Thomas
    Thomas is a common surname of English and Welsh origin, derived from the given name Thomas and borne by numerous notable individuals worldwide.
  • C. 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."
  • D. Thomas
    Thomas is the given first name of English actor Tom Sturridge, known for his work in film, television, and theatre.
  • E. 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.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d710410a04819090036597ac0d271c completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69dbd9df306881908aef5c6e8b4e78dc completed April 12, 2026, 5:43 p.m.
NEDg Description generation batch_69dcad07b51081908fd66ee9ff7341f6 completed April 13, 2026, 8:44 a.m.
NED2 Entity disambiguation (via description) batch_69dd4386e3308190bb8503ce75fa628f completed April 13, 2026, 7:27 p.m.
Created at: April 8, 2026, 9:14 p.m.