Triple

T24225737
Position Surface form Disambiguated ID Type / Status
Subject An Odor of Verbena E601588 entity
Predicate symbolismOfVerbena P24024 FINISHED
Object endurance of memory LITERAL 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: endurance of memory | Statement: [An Odor of Verbena, symbolismOfVerbena, endurance of memory]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: symbolismOfVerbena
Context triple: [An Odor of Verbena, symbolismOfVerbena, endurance of memory]
  • A. plantSymbolism
    Indicates that a plant is associated with a particular symbolic meaning, concept, or value.
  • B. languageOfSymbolism
    Indicates that one entity is the language in which the symbolic meaning or symbolism of another entity is expressed or encoded.
  • C. symbolismIn
    Indicates that one entity functions as a symbol or representation within the context, meaning, or interpretive framework of another entity.
  • D. flowerSymbolMeaning chosen
    Indicates that a particular flower is used to represent or convey a specific symbolic meaning or message.
  • E. symbolismFocus
    Indicates that the primary emphasis of a work, element, or representation is on its symbolic meaning rather than its literal or functional aspects.
  • F. None of above.

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_69e29537ca548190b94a37ebe1977caf completed April 17, 2026, 8:16 p.m.
NER Named-entity recognition batch_69f287df14148190ac2dd00bc248ebd2 completed April 29, 2026, 10:36 p.m.
PD Predicate disambiguation batch_69f1c448abec8190b87cbf9ed419a309 completed April 29, 2026, 8:41 a.m.
Created at: April 18, 2026, midnight