Triple

T12008565
Position Surface form Disambiguated ID Type / Status
Subject Joe Blake E285846 entity
Predicate worksFor P5820 FINISHED
Object John Smith
John Smith is a professional employer or business figure who has Joe Blake among his staff or associates.
E960432 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 Smith | Statement: [Joe Blake, worksFor, John Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Smith
Context triple: [Joe Blake, worksFor, John Smith]
  • A. John
    John is the formal first name of Johnny Most, the famed American sports broadcaster known for his passionate radio commentary of Boston Celtics basketball games.
  • B. John
    John L. Hennessy is an American computer scientist and academic leader best known as a pioneer of RISC architecture and as the former president of Stanford University.
  • C. John
    John is the birth name of American actor, singer, and dancer Jack Haley, best known for playing the Tin Man in the classic film "The Wizard of Oz."
  • D. John
    John is the given name of John Rushworth Jellicoe, the British admiral who commanded the Grand Fleet at the Battle of Jutland and later served as First Sea Lord and Governor-General of New Zealand.
  • E. John
    John is the given name of John Bodkin Adams, a British physician notorious for being suspected of murdering numerous patients in the mid-20th century.
  • 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 Smith
Triple: [Joe Blake, worksFor, John Smith]
Generated description
John Smith is a professional employer or business figure who has Joe Blake among his staff or associates.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Smith
Target entity description: John Smith is a professional employer or business figure who has Joe Blake among his staff or associates.
  • A. John Smith
    John Smith is an individual known primarily as the husband of Jane Smith.
  • B. John Smith
    John Smith is an actor known for appearing in the film "For Men Only."
  • C. John Smith
    John Smith is a person whose formal given name is John but who is also known by the nickname Johnny Smith.
  • D. John Smith
    John Smith was a British politician who served as Leader of the Labour Party and Leader of the Opposition in the early 1990s until his sudden death in 1994.
  • E. John Smith
    John Smith was a delegate from South Carolina who served in the Continental Congress during the American Revolutionary era.
  • 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_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903d61a4c81909e6cb6500b61df94 completed April 10, 2026, 2:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69f48b1570208190a08c64e028f67d81 completed May 1, 2026, 11:14 a.m.
NEDg Description generation batch_69f48fc6da4c81908442f18cb4a65b27 completed May 1, 2026, 11:34 a.m.
NED2 Entity disambiguation (via description) batch_69f495cc50908190aab4f8ca64c66ef3 completed May 1, 2026, noon
Created at: April 8, 2026, 9:46 p.m.