Triple

T3003
Position Surface form Disambiguated ID Type / Status
Subject Herbert Hoover E56 entity
Predicate familyName P18 FINISHED
Object Hoover E56 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: Hoover | Statement: [Herbert Hoover, familyName, Hoover]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hoover
Context triple: [Herbert Hoover, familyName, Hoover]
  • A. Herbert Hoover chosen
    Herbert Hoover was the 31st president of the United States, known for his humanitarian relief efforts during and after World War I and for leading the country at the onset of the Great Depression.
  • B. Theodor
    Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
  • C. Douglas
    Douglas is a masculine given name of Scottish origin that has been widely used in English-speaking countries.
  • D. Harold A. Wheeler
    Harold A. Wheeler was an influential American electrical engineer and inventor known for his pioneering contributions to radio and radar technology.
  • E. James Roosevelt I
    James Roosevelt I was an American businessman and prominent member of the Roosevelt family, best known as the father of U.S. President Franklin D. Roosevelt.
  • 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_69a2328f0e848190ac2840eaf2d5ebd2 completed Feb. 28, 2026, 12:10 a.m.
NER Named-entity recognition batch_69a233c52368819093215a9c745f264c completed Feb. 28, 2026, 12:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69a238e23e0881909815d2dad067d7a1 completed Feb. 28, 2026, 12:37 a.m.
Created at: Feb. 28, 2026, 12:13 a.m.