Triple

T17728945
Position Surface form Disambiguated ID Type / Status
Subject Frank Proffitt E442538 entity
Predicate name P16 FINISHED
Object Frank Proffitt 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: Frank Proffitt | Statement: [Frank Proffitt, name, Frank Proffitt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Proffitt
Context triple: [Frank Proffitt, name, Frank Proffitt]
  • A. Frank Proffitt chosen
    Frank Proffitt was an American Appalachian folk musician and ballad singer known for preserving and popularizing traditional songs such as "Tom Dooley."
  • B. Ray Colcord
    Ray Colcord was an American record producer and composer best known for his work in rock music and for scoring numerous television shows.
  • C. Joe Noland
    Joe Noland is a fictional character from the television series "The District," which follows the professional and personal lives of law enforcement officials in Washington, D.C.
  • D. John Farris
    John Farris is an American novelist and screenwriter best known for his horror and suspense fiction, including the novel that inspired Brian De Palma’s film "The Fury."
  • E. Jerry Finnerman
    Jerry Finnerman was an American cinematographer best known for his visually distinctive work on the original Star Trek television series.
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e478e4ae5c8190a6f0743f7e74b5bf completed April 19, 2026, 6:40 a.m.
Created at: April 10, 2026, 10:08 a.m.