Triple

T4280043
Position Surface form Disambiguated ID Type / Status
Subject Amazon Kinesis Data Firehose E97124 entity
Predicate supportsFormatConversion P14329 FINISHED
Object JSON to Parquet 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: JSON to Parquet | Statement: [Amazon Kinesis Data Firehose, supportsFormatConversion, JSON to Parquet]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: supportsFormatConversion
Context triple: [Amazon Kinesis Data Firehose, supportsFormatConversion, JSON to Parquet]
  • A. allowsConversionTo chosen
    Indicates that one entity permits or enables transformation or change into another specified form or state.
  • B. operatesInFormat
    Indicates that an entity functions, performs its role, or is carried out using a specified format.
  • C. canImportFormat
    Indicates that an entity has the capability to import or read data in a specified format.
  • D. acceptsConversionFrom
    Indicates that one entity can validly receive or handle a conversion from another entity’s type, format, or representation.
  • E. convertsFrom
    Indicates that one entity is transformed or changed into another entity, with the source being the starting form or state.
  • 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_69b34544be3c819084d1ab82d29f90c5 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b350367da48190b735deef9b5d2d2e completed March 12, 2026, 11:45 p.m.
PD Predicate disambiguation batch_69b347fc4c0c8190a7fcd814e27308a5 completed March 12, 2026, 11:10 p.m.
Created at: March 12, 2026, 11:07 p.m.