Triple

T25580418
Position Surface form Disambiguated ID Type / Status
Subject Thunder E641224 entity
Predicate isUsedMetaphoricallyFor P93472 FINISHED
Object divine wrath 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: divine wrath | Statement: [Thunder, isUsedMetaphoricallyFor, divine wrath]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isUsedMetaphoricallyFor
Context triple: [Thunder, isUsedMetaphoricallyFor, divine wrath]
  • A. hasMetaphoricalForm
    Indicates that one entity is expressed, represented, or understood through a metaphorical form or figurative expression involving another entity.
  • B. figurativeMeaning chosen
    Indicates that one entity is used in a non-literal, metaphorical, or symbolic sense to convey a meaning about another entity or concept.
  • C. metaphoricallyOpposes
    Indicates a figurative or symbolic opposition between two entities, where one concept stands in contrast to or challenges the other in a non-literal, metaphorical sense.
  • D. hasMetaphoricalSubject
    Indicates that one entity functions as the metaphorical subject or source domain in a figurative or metaphorical expression involving another entity.
  • E. hasMetaphoricalContent
    Indicates that something contains or expresses meaning through metaphorical, rather than purely literal, content.
  • 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_69e75dc42b588190a98b58e0df359674 completed April 21, 2026, 11:21 a.m.
NER Named-entity recognition batch_69f5f934be208190aed5a7f6a44b6b83 completed May 2, 2026, 1:16 p.m.
PD Predicate disambiguation batch_69f49377411c8190b2188de444d76795 completed May 1, 2026, 11:50 a.m.
Created at: April 21, 2026, 4:11 p.m.