Triple

T9112978
Position Surface form Disambiguated ID Type / Status
Subject Matthew Beard E218648 entity
Predicate name P16 FINISHED
Object Matthew Beard E218648 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: Matthew Beard | Statement: [Matthew Beard, name, Matthew Beard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Beard
Context triple: [Matthew Beard, name, Matthew Beard]
  • A. Matthew Beard chosen
    Matthew Beard is a British actor known for his roles in films such as "The Imitation Game" and various television and stage productions.
  • B. Matt Beard
    Matt Beard is an English football manager known for coaching top women’s clubs, including a stint in the National Women's Soccer League with the Boston Breakers.
  • C. Paul Beard
    Paul Beard is a British guitarist and musical director best known for his work with artists such as James Blunt.
  • D. Charlie Bewley
    Charlie Bewley is a British actor best known for his roles in the Twilight film series and various independent films and television dramas.
  • E. Mark Bennett
    Mark Bennett is a theatrical sound designer known for his work on major stage productions, including the Broadway trilogy "The Coast of Utopia."
  • 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_69ca83dc94ac8190b9ef42684d36ff39 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca84b0a048190964f560f78e27cce completed April 1, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d03052716c8190835b0d3357a29ce5 completed April 3, 2026, 9:25 p.m.
Created at: March 30, 2026, 7:16 p.m.