Triple

T19858189
Position Surface form Disambiguated ID Type / Status
Subject John E477188 entity
Predicate hasDiminutive P456 FINISHED
Object Johnny NE NERFINISHED

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: Johnny | Statement: [John, hasDiminutive, Johnny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johnny
Context triple: [John, hasDiminutive, Johnny]
  • A. Johnny chosen
    Johnny is a common English masculine given name, often used as a familiar or diminutive form of John.
  • B. Johnny
    Johnny is the abrasive, intellectually sharp yet self-destructive drifter who serves as the central antihero of Mike Leigh’s 1993 British film "Naked."
  • C. Jerry
    Jerry is the given name of Jerry Lee Lewis, the influential American rock and roll and country music singer and pianist known for hits like "Great Balls of Fire."
  • D. Jerry
    Jerry is a masculine given name commonly used in English-speaking countries, often as a diminutive of names like Gerald, Jerome, or Jeremy.
  • E. Jerry
    Jerry is the video store clerk protagonist of the comedy film "Be Kind Rewind," known for recreating erased movies with homemade, low-budget remakes.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6586dbbf0819089e7157d416aeaaf completed April 20, 2026, 4:46 p.m.
Created at: April 10, 2026, 1:51 p.m.