Triple

T9906361
Position Surface form Disambiguated ID Type / Status
Subject Milk E185021 entity
Predicate editedBy P1954 FINISHED
Object Elliot Graham E389654 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: Elliot Graham | Statement: [Milk, editedBy, Elliot Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elliot Graham
Context triple: [Milk, editedBy, Elliot Graham]
  • A. Elliot Graham chosen
    Elliot Graham is a film editor known for his work on major feature films, including the James Bond movie "No Time to Die."
  • B. Emun Elliott
    Emun Elliott is a Scottish actor known for his work in film and television, including roles in projects such as the sci-fi film "Prometheus."
  • C. Josh Graham
    Josh Graham is a visual artist and designer known for creating album artwork and multimedia visuals for prominent rock and metal bands.
  • D. Jaki Graham
    Jaki Graham is a British R&B and soul singer best known for her 1980s hits and powerful vocal performances, including successful covers of classic songs.
  • E. Andrew Gant
    Andrew Gant is a British composer, singer, author, and academic known for his work in choral music and his writings on the history of English church music and carols.
  • 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_69ca8296165881908ca4750701af1f29 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb50cf8808190a41e565216712704 completed April 2, 2026, 12:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1eb316a188190a1c7fbe0d1997cf5 completed April 5, 2026, 4:55 a.m.
Created at: March 30, 2026, 8:40 p.m.