Triple

T14123222
Position Surface form Disambiguated ID Type / Status
Subject Violet Harmon E339954 entity
Predicate associatedWith P37 FINISHED
Object Larry Harvey E327880 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: Larry Harvey | Statement: [Violet Harmon, associatedWith, Larry Harvey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry Harvey
Context triple: [Violet Harmon, associatedWith, Larry Harvey]
  • A. Larry Harvey chosen
    Larry Harvey is a fictional character from the television series "American Horror Story," known for his sinister and violent role in the first season, "Murder House."
  • B. Larry Harvey
    Larry Harvey was an American artist and activist best known as the co-founder of the Burning Man festival in Nevada’s Black Rock Desert.
  • C. Richard Hagen
    Richard Hagen is a theoretical physicist best known as one of the co-discoverers of the Higgs mechanism in particle physics.
  • D. Herman Wittwer
    Herman Wittwer was an American entrepreneur best known as the founder of the major U.S. insurer American Family Insurance.
  • E. Harry Karl
    Harry Karl was an American shoe magnate and businessman best known for his high-profile marriages to Hollywood actresses, including Debbie Reynolds.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de6095548881908a9e66adccca92d2 completed April 14, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6476c15881909881b9f85697a9b2 completed May 8, 2026, 4:20 a.m.
Created at: April 9, 2026, 10:22 p.m.