Triple

T12757161
Position Surface form Disambiguated ID Type / Status
Subject Bernarda Bryson Shahn E304888 entity
Predicate hasChild P369 FINISHED
Object Ezra Shahn E53085 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: Ezra Shahn | Statement: [Bernarda Bryson Shahn, hasChild, Ezra Shahn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ezra Shahn
Context triple: [Bernarda Bryson Shahn, hasChild, Ezra Shahn]
  • A. Ben Shahn chosen
    Ben Shahn was a Lithuanian-born American social realist artist and photographer known for his politically engaged murals, paintings, and documentary photographs of working-class life during the Great Depression.
  • B. Carl Mydans
    Carl Mydans was an American photojournalist best known for his powerful documentary images of the Great Depression and World War II, including work for the Farm Security Administration and Life magazine.
  • C. Reginald Marsh
    Reginald Marsh was an American painter and printmaker best known for his vivid, crowded depictions of New York City’s urban life during the early 20th century.
  • D. Jim van der Zee
    Jim van der Zee is a Dutch singer known for winning the talent show The Voice of Holland.
  • E. Charles Sheeler
    Charles Sheeler was an American painter and photographer known for his pioneering role in Precisionism and his stark, modernist depictions of industrial architecture.
  • 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_69d7bdf1fcd081909ffb0e0d6fa3a07d completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96d8b57b88190b29b8fdca415c81c completed April 10, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c0dd657c8190b69e8bf187034360 completed May 3, 2026, 3:28 a.m.
Created at: April 9, 2026, 5:27 p.m.