Triple

T19507983
Position Surface form Disambiguated ID Type / Status
Subject George Devey E488075 entity
Predicate name P16 FINISHED
Object George Devey 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 Devey | Statement: [George Devey, name, George Devey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Devey
Context triple: [George Devey, name, George Devey]
  • A. George Devey chosen
    George Devey was a 19th-century English architect known for his picturesque country houses and influential role in the development of the Queen Anne Revival style.
  • B. George Dilboy
    George Dilboy was a Greek-American U.S. Army soldier and Medal of Honor recipient recognized for his heroism during World War I.
  • C. Frank Debenham
    Frank Debenham was an Australian geologist and Antarctic explorer who became a leading authority on polar research and helped establish it as an academic discipline.
  • D. Michael Dowse
    Michael Dowse is a Canadian film and television director known for energetic, character-driven comedies such as "Fubar," "Goon," and the action-comedy "Stuber."
  • E. Joseph Blatchley
    Joseph Blatchley is a British actor and director known for his work in film, television, and theatre, including a role in François Truffaut’s film "The Story of Adèle H."
  • 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_69d8e8d9d1c88190b01cd78b8be49384 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e635130e708190bb3d70e1abbade2a completed April 20, 2026, 2:15 p.m.
Created at: April 10, 2026, 1:40 p.m.