Triple

T18706331
Position Surface form Disambiguated ID Type / Status
Subject John Eaton E457376 entity
Predicate name P16 FINISHED
Object John Henry Eaton 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 Henry Eaton | Statement: [John Eaton, name, John Henry Eaton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Henry Eaton
Context triple: [John Eaton, name, John Henry Eaton]
  • A. John Eaton chosen
    John Eaton was a 19th-century American politician and U.S. Secretary of War under President Andrew Jackson.
  • B. Elias Polk
    Elias Polk was an enslaved man who served President James K. Polk and later became a notable political figure and advocate for African American rights during Reconstruction.
  • C. James J. White
    James J. White was a prominent Boston civic leader and benefactor in whose honor White Stadium was named.
  • D. George Crook Hayes
    George Crook Hayes was a son of U.S. President Rutherford B. Hayes, belonging to the prominent Hayes political family of the 19th century.
  • E. James Polk Johnson
    James Polk Johnson was a 19th-century American settler and early landowner in Texas after whom the town of Johnson City was named.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671717b88190974f542015f641e8 completed April 19, 2026, 11:36 p.m.
Created at: April 10, 2026, 11:50 a.m.