Triple

T17544487
Position Surface form Disambiguated ID Type / Status
Subject Rodger Dodger E427289 entity
Predicate editedBy P1954 FINISHED
Object Andy Keir 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: Andy Keir | Statement: [Rodger Dodger, editedBy, Andy Keir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Keir
Context triple: [Rodger Dodger, editedBy, Andy Keir]
  • A. Andrew Keir chosen
    Andrew Keir was a Scottish character actor best known for his roles in British film and television, including notable appearances in Hammer horror productions.
  • B. Joss Ackland
    Joss Ackland is a distinguished English actor known for his extensive film, television, and stage career, often portraying authoritative or villainous characters.
  • C. Peter Donovan
    Peter Donovan is the husband of acclaimed American actress and singer Audra McDonald.
  • D. Anthony Ainley
    Anthony Ainley was an English actor best known for playing the villainous Time Lord known as the Master in the long-running British science fiction series Doctor Who.
  • E. Reggie Brown
    Reggie Brown is an American entrepreneur best known as a co-founder of Snapchat, the multimedia messaging app developed by Snap Inc.
  • 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e454609bdc8190b81b362906e7e3fd completed April 19, 2026, 4:04 a.m.
Created at: April 10, 2026, 5:49 a.m.