Triple

T20293290
Position Surface form Disambiguated ID Type / Status
Subject George Donner E510080 entity
Predicate name P16 FINISHED
Object George Donner 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: George Donner | Statement: [George Donner, name, George Donner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Donner
Context triple: [George Donner, name, George Donner]
  • A. George Donner chosen
    George Donner was an American pioneer and leader of the ill-fated Donner Party wagon train that became trapped in the Sierra Nevada during the winter of 1846–1847.
  • B. Samuel Ballard
    Samuel Ballard is a fictional barrister and conservative, somewhat pompous head of chambers in John Mortimer’s Rumpole of the Bailey stories.
  • C. Francis Anthony Donner
    Francis Anthony Donner was the birth name of Frank Fay, an American stage and film actor and vaudeville comedian prominent in the early 20th century.
  • D. Charles Driggs
    Charles Driggs is the uptight New York businessman whose impulsive adventure with a free-spirited woman drives the plot of the 1986 film "Something Wild."
  • E. John Fanning
    John Fanning is an American entrepreneur best known for co-founding the pioneering peer-to-peer file sharing service Napster.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e677024de08190bfa54ae26b5486d1 completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:12 a.m.