Triple

T23288769
Position Surface form Disambiguated ID Type / Status
Subject Georgia Young E589966 entity
Predicate hasCloseFriend P49697 FINISHED
Object Violet 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: Violet | Statement: [Georgia Young, hasCloseFriend, Violet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Violet
Context triple: [Georgia Young, hasCloseFriend, Violet]
  • A. Violet
    Violet is a live-action short film recognized with the Academy Award for Best Live Action Short Film at the 54th Oscars.
  • B. Violet
    Violet is the given first name of the English actress Anne Heywood, known for her film and television roles in the mid-20th century.
  • C. Violet
    Violet is the given name of Helen Violet Asquith, a British aristocrat and social figure of the early 20th century.
  • D. Violet
    Violet is the former nickname associated with New York University’s athletic teams, historically reflecting the school’s signature color.
  • E. Violet
    Violet is a feminine given name often associated with the purple flower and the color violet, conveying themes of beauty and delicacy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69e25d1af9d88190a0b9b5e8fa608618 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19649570c8190b565fafa55b1f886 completed April 29, 2026, 5:25 a.m.
Created at: April 17, 2026, 5:01 p.m.