Triple

T30520459
Position Surface form Disambiguated ID Type / Status
Subject Gram E776679 entity
Predicate testDescribedAs P11875 FINISHED
Object cutting an anvil in the Völsunga saga 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: cutting an anvil in the Völsunga saga | Statement: [Gram, testDescribedAs, cutting an anvil in the Völsunga saga]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: testDescribedAs
Context triple: [Gram, testDescribedAs, cutting an anvil in the Völsunga saga]
  • A. describedIn
    Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
  • B. describedFrom
    Indicates that something is characterized, explained, or defined based on information, perspective, or features originating from a particular source or reference point.
  • C. describedAt
    Indicates that something is explained, characterized, or detailed in a particular source, context, or location.
  • D. isDescriptive
    Indicates that one entity provides a description or characterization of another entity.
  • E. hasDescription chosen
    Indicates that an entity is associated with a textual description that explains or characterizes it.
  • 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_69f2249b23c4819087fa85496d92f43f completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f68809fa4c8190b7477043dd360dc2 completed May 2, 2026, 11:26 p.m.
PD Predicate disambiguation batch_69f67e42d6688190b60e91d2c388c555 completed May 2, 2026, 10:44 p.m.
Created at: April 29, 2026, 8:17 p.m.