Triple

T19903753
Position Surface form Disambiguated ID Type / Status
Subject Spratt E478358 entity
Predicate hasNotableBearer P458 FINISHED
Object John M. Spratt Jr. 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 M. Spratt Jr. | Statement: [Spratt, hasNotableBearer, John M. Spratt Jr.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John M. Spratt Jr.
Context triple: [Spratt, hasNotableBearer, John M. Spratt Jr.]
  • A. John Spratt chosen
    John Spratt is an American Democratic politician who long represented South Carolina's 5th congressional district in the U.S. House of Representatives and was known for his work on budget and defense issues.
  • B. Robin Grassley
    Robin Grassley is a child of longtime U.S. Senator Chuck Grassley of Iowa.
  • C. Barney Frank
    Barney Frank is a former U.S. Congressman from Massachusetts who played a leading role in financial regulatory reform and co-authored the Dodd–Frank Act.
  • D. Thomas J. Dodd
    Thomas J. Dodd was an American lawyer, prosecutor at the Nuremberg Trials, and long-serving U.S. Senator from Connecticut.
  • E. Carl Levin
    Carl Levin was a long-serving U.S. Senator from Michigan known for his leadership on national security and defense oversight, including as chair of the Senate Armed Services 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65944c55481909b54a8f9a9c087d6 completed April 20, 2026, 4:50 p.m.
Created at: April 10, 2026, 1:52 p.m.