Triple

T19009860
Position Surface form Disambiguated ID Type / Status
Subject Richard Tandy E465192 entity
Predicate familyName P18 FINISHED
Object Tandy 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: Tandy | Statement: [Richard Tandy, familyName, Tandy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tandy
Context triple: [Richard Tandy, familyName, Tandy]
  • A. Tandy chosen
    Tandy is a surname most notably associated with Jessica Tandy, the acclaimed British-American actress known for her work on stage and in film.
  • B. Tandy
    Tandy is a short story within Sherwood Anderson’s 1919 collection "Winesburg, Ohio," focusing on themes of longing, identity, and spiritual yearning in small-town America.
  • C. Vertner Woodson Tandy
    Vertner Woodson Tandy was an American architect and trailblazing African American professional, best known as one of the Seven Jewels who co-founded the Alpha Phi Alpha fraternity.
  • D. Tandem Computers
    Tandem Computers was a pioneering American computer company best known for its fault-tolerant, high-availability systems used in mission-critical transaction processing.
  • E. Tandy TRS-80
    The Tandy TRS-80 was one of the earliest mass-market personal computers, popular in the late 1970s and early 1980s for home and small business use.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6a8225c81908e80ae7eb1c1301b completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:02 p.m.