Triple

T18778155
Position Surface form Disambiguated ID Type / Status
Subject Congressional Black Caucus E459184 entity
Predicate foundedBy P104 FINISHED
Object John Conyers NE NERFINISHED

How this triple was built (2 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 Conyers | Statement: [Congressional Black Caucus, foundedBy, John Conyers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Conyers
Context triple: [Congressional Black Caucus, foundedBy, John Conyers]
  • A. John Conyers chosen
    John Conyers was a long-serving Democratic U.S. Representative from Michigan and a founding member of the Congressional Black Caucus.
  • B. Charles B. Rangel
    Charles B. Rangel is a longtime Democratic politician and former U.S. Representative from New York who became one of the most influential African American lawmakers in Congress.
  • C. Charles Diggs
    Charles Diggs was an influential African American U.S. Congressman from Michigan who became a leading advocate for civil rights and Black political representation.
  • D. W. D. Conyers
    W. D. Conyers was a prominent figure in Georgia’s history after whom the city of Conyers was named.
  • E. Sander Levin
    Sander Levin is an American Democratic politician who represented Michigan in the U.S. House of Representatives for over three decades and chaired the House Ways and Means Committee.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d396f54c8190ba49db31e8743842 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5933c640081909bb6fbaa1a21d411 completed April 20, 2026, 2:45 a.m.
Created at: April 10, 2026, 11:52 a.m.