Triple

T10747466
Position Surface form Disambiguated ID Type / Status
Subject John Harvey Kellogg E253487 entity
Predicate givenName P17 FINISHED
Object John
John Harvey Kellogg was an American medical doctor, nutritionist, and health reformer best known for developing corn flakes and promoting vegetarianism and wellness at the Battle Creek Sanitarium.
E885266 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 | Statement: [John Harvey Kellogg, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Harvey Kellogg, givenName, John]
  • A. John
    John is the husband of Martha Rainsborough.
  • B. John
    John is the first name of J. Michael Luttig, a prominent American conservative jurist and former federal appellate judge.
  • C. John
    John J. McCloy was an influential American lawyer, banker, and statesman who served in key roles such as U.S. High Commissioner for Germany and president of the World Bank.
  • D. John
    John is the given name of John Howard, an Australian politician who served as the 25th Prime Minister of Australia.
  • E. John
    John is a fictional police detective and main character from the science fiction TV series "Almost Human."
  • 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
Triple: [John Harvey Kellogg, givenName, John]
Generated description
John Harvey Kellogg was an American medical doctor, nutritionist, and health reformer best known for developing corn flakes and promoting vegetarianism and wellness at the Battle Creek Sanitarium.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John Harvey Kellogg was an American medical doctor, nutritionist, and health reformer best known for developing corn flakes and promoting vegetarianism and wellness at the Battle Creek Sanitarium.
  • A. John
    John is the middle name of American entrepreneur Henry John Heinz, founder of the H. J. Heinz Company known for its ketchup and other food products.
  • B. John
    John is the given name of John M. Olin, an American industrialist and philanthropist known for his leadership of the Olin Corporation and his influential charitable foundation.
  • C. John
    John is the given name of John Henry Patterson, an American industrialist and founder of the National Cash Register Company.
  • D. John
    John is the given name of John Milton Gregory, a 19th-century American educator and university president known for helping to found the University of Illinois.
  • E. John
    John is the given name of John Hays Hammond Jr., an American inventor known for his pioneering work in radio control and naval weaponry.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d711b9242c81908dbf3fa155159b3c completed April 9, 2026, 2:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69de55a12b8c8190bbeeb6d176f42b49 completed April 14, 2026, 2:56 p.m.
NEDg Description generation batch_69de5952f6c48190abd3b87372d54f58 completed April 14, 2026, 3:12 p.m.
NED2 Entity disambiguation (via description) batch_69de5ed49c9c8190a4085407f88d7a05 completed April 14, 2026, 3:35 p.m.
Created at: April 8, 2026, 9:15 p.m.