Triple

T7979840
Position Surface form Disambiguated ID Type / Status
Subject John Sarbanes E185542 entity
Predicate givenName P17 FINISHED
Object John
John Sarbanes is an American politician and attorney who has served as a Democratic member of the U.S. House of Representatives from Maryland.
E702083 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 Sarbanes, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Sarbanes, givenName, John]
  • A. John
    John is the given first name of J. Edgar Hoover, the long-serving and influential first director of the United States Federal Bureau of Investigation (FBI).
  • B. John
    John is the given name of the late American comedian and actor John Belushi, famed for his work on "Saturday Night Live" and in films like "Animal House" and "The Blues Brothers."
  • C. John
    John is the given name of the influential American jazz saxophonist and composer John Coltrane.
  • D. John
    John is the given name of John Stevens Henslow, the 19th-century English clergyman, botanist, and mentor to Charles Darwin.
  • E. John
    John is the birth name of American character actor Jack Warden, known for his prolific film and television career 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
Triple: [John Sarbanes, givenName, John]
Generated description
John Sarbanes is an American politician and attorney who has served as a Democratic member of the U.S. House of Representatives from Maryland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John Sarbanes is an American politician and attorney who has served as a Democratic member of the U.S. House of Representatives from Maryland.
  • A. John
    John E. Sununu is an American politician and engineer who served as a U.S. Representative and U.S. Senator from New Hampshire.
  • B. John
    John is the first name of Dennis Hastert, the former Speaker of the United States House of Representatives.
  • C. John
    John Fetterman is an American politician serving as the junior United States senator from Pennsylvania and former lieutenant governor of the state.
  • D. John
    John is the given name of John Edward Fogarty, an American politician who served as a U.S. Representative from Rhode Island.
  • E. John
    John Lewis was a prominent American civil rights leader and long-serving U.S. Congressman known for his key role in the struggle for racial equality.
  • 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_69ca829851908190b4e03829353ee7c3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c261904819086910898071f3629 completed March 31, 2026, 3:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbdef32d4c8190a2e5c76d2db6c45f completed March 31, 2026, 2:49 p.m.
NEDg Description generation batch_69cbe43e47048190a0044477f88de5d0 completed March 31, 2026, 3:11 p.m.
NED2 Entity disambiguation (via description) batch_69cc0d60254c819087d1de7ca6ea554b completed March 31, 2026, 6:07 p.m.
Created at: March 30, 2026, 5:14 p.m.