Triple

T19688422
Position Surface form Disambiguated ID Type / Status
Subject Kellogg E472772 entity
Predicate hasNotableBearer P458 FINISHED
Object Frank B. Kellogg 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: Frank B. Kellogg | Statement: [Kellogg, hasNotableBearer, Frank B. Kellogg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank B. Kellogg
Context triple: [Kellogg, hasNotableBearer, Frank B. Kellogg]
  • A. Frank B. Kellogg chosen
    Frank B. Kellogg was an American lawyer, diplomat, and U.S. Secretary of State who won the Nobel Peace Prize for his role in advancing international peace efforts in the early 20th century.
  • B. Francis William Kellogg
    Francis William Kellogg was a 19th-century American politician and U.S. Representative from Michigan who served during and after the Civil War era.
  • C. Harold H. Seward
    Harold H. Seward was an American computer scientist known for his contributions to sorting algorithms and early work in computer science theory.
  • D. Cordell Hull
    Cordell Hull was a long-serving U.S. Secretary of State under President Franklin D. Roosevelt and a key architect of both the United Nations and major World War II–era diplomacy.
  • E. Clement Biddle Wood
    Clement Biddle Wood was a screenwriter best known for his work on the cult science-fiction film "Barbarella."
  • 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_69d8e515bef88190bc30781aea50537a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6420e5b788190a63ff6b83383b0e8 completed April 20, 2026, 3:11 p.m.
Created at: April 10, 2026, 1:45 p.m.