Triple

T13995021
Position Surface form Disambiguated ID Type / Status
Subject Rishi Rich E336672 entity
Predicate collaboratedWith P435 FINISHED
Object Craig David E605561 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: Craig David | Statement: [Rishi Rich, collaboratedWith, Craig David]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig David
Context triple: [Rishi Rich, collaboratedWith, Craig David]
  • A. Craig David chosen
    Craig David is a British singer, songwriter, and record producer best known for his early-2000s UK garage and R&B hits such as "Fill Me In" and "7 Days."
  • B. Peter André
    Peter André is a British-Australian pop singer and television personality who rose to fame in the 1990s with hits like "Mysterious Girl."
  • C. Craig Martin
    Craig Martin is an American actor and producer best known as one of the sons of legendary entertainer Dean Martin.
  • D. Gary Jules
    Gary Jules is an American singer-songwriter best known for his haunting cover of "Mad World," which gained widespread recognition through its use in the film Donnie Darko.
  • E. James Blunt
    James Blunt is an English singer-songwriter and former British Army officer best known for his hit single "You're Beautiful" and the album "Back to Bedlam."
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb53f508190855cd69b8061dd77 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9d4a54819091c7efbeb4dcc5f7 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.