Triple

T17119962
Position Surface form Disambiguated ID Type / Status
Subject Sam Brownback E415437 entity
Predicate precededBy P97 FINISHED
Object Bob Dole E45418 NE FINISHED

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: Bob Dole | Statement: [Sam Brownback, precededBy, Bob Dole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bob Dole
Context triple: [Sam Brownback, precededBy, Bob Dole]
  • A. Bob Dole chosen
    Bob Dole was a long-serving Republican U.S. senator from Kansas and 1996 presidential nominee known for his influential legislative work and party leadership.
  • B. Clare Quayle
    Clare Quayle is a character from the espionage thriller television series "Homeland," portrayed by actress Nazanin Boniadi.
  • C. Mac Quayle
    Mac Quayle is an Emmy-winning American composer best known for his atmospheric, electronic-driven scores for television series such as Mr. Robot and American Horror Story.
  • D. Dan Quayle
    Dan Quayle is an American politician and lawyer who served as the 44th vice president of the United States from 1989 to 1993 under President George H. W. Bush.
  • E. Ross Perot
    Ross Perot was an American billionaire businessman and influential third-party presidential candidate who helped reshape U.S. politics in the 1990s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3e8092b548190b45c1695be47edc2 completed April 18, 2026, 8:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a013a0e11108190bfcf858142aa9ff3 completed May 11, 2026, 2:08 a.m.
Created at: April 10, 2026, 5:36 a.m.