Triple

T3451014
Position Surface form Disambiguated ID Type / Status
Subject Roku E72793 entity
Predicate founder P104 FINISHED
Object Anthony Wood E384635 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: Anthony Wood | Statement: [Roku, founder, Anthony Wood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony Wood
Context triple: [Roku, founder, Anthony Wood]
  • A. Anthony Wood chosen
    Anthony Wood is a technology entrepreneur best known as the founder and CEO of Roku, a leading streaming media platform.
  • B. Philip Woodruff
    Philip Woodruff was the pen name of British civil servant Philip Mason, best known for his influential writings on the British Raj and the Indian Civil Service.
  • C. John Lyons
    John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
  • D. Richard Bristow
    Richard Bristow was a 16th-century English Catholic scholar and theologian who contributed to the development and annotation of the Douay–Rheims Bible.
  • E. Christopher Fairbank
    Christopher Fairbank is a British character actor known for his distinctive features and roles in film and television, including appearances in productions such as "Auf Wiedersehen, Pet" and various Shakespearean adaptations.
  • 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_69ad85b12a908190a1d10a6b03b4f8ae completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adba7465248190947f9096e230e1c4 completed March 8, 2026, 6:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4e4d1c7188190b0f98fdc51e6684a completed March 14, 2026, 4:32 a.m.
Created at: March 8, 2026, 3:16 p.m.