Triple

T12483733
Position Surface form Disambiguated ID Type / Status
Subject Ben Shahn E298377 entity
Predicate familyName P18 FINISHED
Object Shahn E298377 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: Shahn | Statement: [Ben Shahn, familyName, Shahn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shahn
Context triple: [Ben Shahn, familyName, Shahn]
  • A. Shahn chosen
    Shahn is a surname most notably associated with Ben Shahn, a Lithuanian-born American artist known for his social realism and political activism.
  • B. Vinoodh Matadin
    Vinoodh Matadin is a Dutch fashion and art photographer best known as one half of the photography duo Inez and Vinoodh, renowned for their influential work in fashion editorials, advertising, and album artwork.
  • C. Alla Rakha
    Alla Rakha was a renowned Indian tabla virtuoso celebrated for his collaborations with sitar maestro Ravi Shankar and for popularizing Indian classical percussion worldwide.
  • D. Jules Bihari
    Jules Bihari was an American record executive and producer best known as one of the Bihari brothers who helped shape postwar blues and early rock and roll through their work with labels like Modern and Kent Records.
  • E. Christian Gazal
    Christian Gazal is a film editor best known for his work on the animated feature "Happy Feet."
  • 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_69d6ada377208190a36011199a4d8558 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94ddf0b6c8190aff4fe267d8f6efe completed April 10, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f29307c8190b024d889d45ba9f7 completed May 2, 2026, 6:15 p.m.
Created at: April 8, 2026, 9:56 p.m.