Triple

T12483618
Position Surface form Disambiguated ID Type / Status
Subject Diane Arbus E298374 entity
Predicate child P120 FINISHED
Object Amy Arbus E985713 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: Amy Arbus | Statement: [Diane Arbus, child, Amy Arbus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amy Arbus
Context triple: [Diane Arbus, child, Amy Arbus]
  • A. Dale Arbus
    Dale Arbus is a dental assistant and one of the three hapless friends plotting to kill their abusive employers in the dark comedy film "Horrible Bosses."
  • B. Doon Arbus chosen
    Doon Arbus is an American writer and curator best known for preserving and promoting the photographic legacy of her mother, Diane Arbus.
  • C. Dorothy Stratten
    Dorothy Stratten was a Canadian Playboy Playmate and rising film actress whose promising career was tragically cut short when she was murdered at age 20 in 1980.
  • D. Elizabeth Short Harrison
    Elizabeth Short Harrison was a member of the prominent Harrison family of Ohio, descended from early American political figures.
  • E. Diane Arbus
    Diane Arbus was an American photographer renowned for her stark, intimate portraits of marginalized and unconventional subjects that challenged traditional notions of beauty and normalcy.
  • 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_69f64ba5efc881909784037b95f7bbe3 completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:56 p.m.