Triple

T31173047
Position Surface form Disambiguated ID Type / Status
Subject David Swan E794664 entity
Predicate literaryDeviceRelation P16928 FINISHED
Object irony 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: irony | Statement: [David Swan, literaryDeviceRelation, irony]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: literaryDeviceRelation
Context triple: [David Swan, literaryDeviceRelation, irony]
  • A. rhetoricalDevice
    Indicates that one entity is used as a rhetorical device in relation to another, such as a figure of speech, stylistic technique, or persuasive strategy within a discourse.
  • B. metafictionalRelation
    Indicates a relationship in which a work, element, or narrative explicitly refers to, comments on, or otherwise draws attention to its own fictional status or construction.
  • C. lyricalDevice
    Indicates the use of a specific poetic or musical technique within lyrics to achieve a particular expressive or aesthetic effect.
  • D. literaryFeature chosen
    Indicates a relationship where something possesses or exhibits a characteristic, device, or stylistic element used in literature.
  • E. intertextualRelation
    Indicates a relationship in which one text references, echoes, or otherwise meaningfully connects to another text.
  • 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_69f224d5b9708190b6ca79ad2fd3a28a completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f74062b9388190b30546cf700a825c completed May 3, 2026, 12:32 p.m.
PD Predicate disambiguation batch_69f73c802b848190b61a416b7488bd96 completed May 3, 2026, 12:16 p.m.
Created at: April 29, 2026, 9:07 p.m.