Triple

T28942540
Position Surface form Disambiguated ID Type / Status
Subject Mangalesha E730489 entity
Predicate supportedArchitectureType P24956 FINISHED
Object rock-cut cave temples 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: rock-cut cave temples | Statement: [Mangalesha, supportedArchitectureType, rock-cut cave temples]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: supportedArchitectureType
Context triple: [Mangalesha, supportedArchitectureType, rock-cut cave temples]
  • A. supportedArchitect
    Indicates that one entity provides architectural backing, endorsement, or assistance to another entity or architectural concept.
  • B. laterSupportedArchitecture
    Indicates that one architecture provides support for another architecture that was introduced or adopted at a later time.
  • C. usesArchitecture chosen
    Indicates that one entity is built, implemented, or operates according to the architectural style, framework, or design specified by another entity.
  • D. supportsGuestArchitecture
    Indicates that one entity provides the necessary capabilities or environment to run or host the specified guest architecture of another entity.
  • E. hasArchitecturalSupport
    Indicates that one entity provides structural or design backing, compatibility, or enablement for another within an architectural context.
  • 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_69f043ea0aa88190a25acbf46157995a completed April 28, 2026, 5:21 a.m.
NER Named-entity recognition batch_6a0224f4b6cc8190a8f79700a9af765f completed May 11, 2026, 6:50 p.m.
PD Predicate disambiguation batch_6a0223f01eb081909419518fdd45f2a4 completed May 11, 2026, 6:46 p.m.
Created at: April 28, 2026, 8:37 a.m.