Triple

T1770672
Position Surface form Disambiguated ID Type / Status
Subject Aunt Sally Phelps E38867 entity
Predicate spouse P13 FINISHED
Object Silas Phelps E39305 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: Silas Phelps | Statement: [Aunt Sally Phelps, spouse, Silas Phelps]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Silas Phelps
Context triple: [Aunt Sally Phelps, spouse, Silas Phelps]
  • A. Silas Phelps chosen
    Silas Phelps is a kindly but morally conflicted Southern farmer and slave owner who appears as Tom Sawyer’s uncle in Mark Twain’s novel "Adventures of Huckleberry Finn."
  • B. Elias Loomis
    Elias Loomis was a 19th-century American mathematician and physicist known for his work in astronomy, meteorology, and mathematical education.
  • C. Samuel March
    Samuel March was one of the early New York stockbrokers who helped found what became the New York Stock Exchange by signing the 1792 Buttonwood Agreement.
  • D. Wilmot Reed
    Wilmot Reed is the given first and middle name of Reed Hastings, the American entrepreneur best known as the co-founder and former CEO of Netflix.
  • E. Ephraim Hartwell
    Ephraim Hartwell was an 18th-century Massachusetts tavern keeper and farmer known for his role in local events around the time of the American Revolution.
  • 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_69a8862e61708190af97b9838cc3f5de completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa648eb9488190b1be2d2b6d259634 completed March 6, 2026, 5:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada9936f5881909b78bda48039916a completed March 8, 2026, 4:53 p.m.
Created at: March 4, 2026, 7:31 p.m.