Triple

T16505122
Position Surface form Disambiguated ID Type / Status
Subject Rufus Sewall E400906 entity
Predicate name P16 FINISHED
Object Rufus Sewall E400906 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: Rufus Sewall | Statement: [Rufus Sewall, name, Rufus Sewall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rufus Sewall
Context triple: [Rufus Sewall, name, Rufus Sewall]
  • A. Rufus Sewall chosen
    Rufus Sewall is a notable individual distinguished enough to be recognized as a prominent bearer of the Sewall surname.
  • B. Theodore Sedgwick
    Theodore Sedgwick was an American lawyer, politician, and jurist who served as Speaker of the U.S. House of Representatives in the late 18th century.
  • C. Winthrop Sargent
    Winthrop Sargent was an American politician and military officer who served in the early United States government, notably as a key territorial administrator on the expanding western frontier.
  • D. Philemon Dickinson
    Philemon Dickinson was an American Revolutionary War officer from New Jersey who gained prominence for leading effective militia operations, particularly during the Forage War against British forces.
  • E. Thomas Hubbard
    Thomas Hubbard is a personal name shared by multiple individuals, including figures in fields such as academia, politics, and business.
  • 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e51ce1c81909548298f703a7ffa completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00607e933c8190ae0572583b5a9cbf completed May 10, 2026, 10:39 a.m.
Created at: April 10, 2026, 5:14 a.m.