Triple

T17209677
Position Surface form Disambiguated ID Type / Status
Subject Donald Ray Pollock E417691 entity
Predicate name P16 FINISHED
Object Donald Ray Pollock E417691 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: Donald Ray Pollock | Statement: [Donald Ray Pollock, name, Donald Ray Pollock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donald Ray Pollock
Context triple: [Donald Ray Pollock, name, Donald Ray Pollock]
  • A. Donald Ray Pollock chosen
    Donald Ray Pollock is an American writer known for his dark, gritty Southern Gothic fiction, including the novel "The Devil All the Time."
  • B. William Pollock
    William Pollock is a relatively common personal name shared by multiple individuals, including figures in fields such as sports, politics, and academia.
  • C. Robert Pollock
    Robert Pollock is a relatively common personal name shared by multiple individuals across fields such as politics, literature, and the arts.
  • D. Charles Pollock
    Charles Pollock was the plaintiff in the landmark 1895 U.S. Supreme Court case Pollock v. Farmers' Loan & Trust Co., which challenged the constitutionality of a federal income tax.
  • E. Robert Ellis Miller
    Robert Ellis Miller was an American film and television director known for his work on character-driven dramas and comedies from the 1960s through the 1980s.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dc4792081909443df7937768ede completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fe217308190b6ae1e98d0c421e4 completed May 11, 2026, 4:49 a.m.
Created at: April 10, 2026, 5:38 a.m.