Triple

T19385070
Position Surface form Disambiguated ID Type / Status
Subject BBB E484911 entity
Predicate scaleContext P93346 FINISHED
Object long-term issuer credit ratings 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: long-term issuer credit ratings | Statement: [BBB, scaleContext, long-term issuer credit ratings]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: scaleContext
Context triple: [BBB, scaleContext, long-term issuer credit ratings]
  • A. scaleProperty
    Indicates that one entity defines or modifies the scale, magnitude, or proportional sizing used to interpret or represent a property of another entity.
  • B. scaleFunction
    Indicates a relationship where one entity defines how another entity’s values are proportionally adjusted or transformed according to a scaling rule or factor.
  • C. scaleDefinition chosen
    Indicates that an entity specifies the parameters, structure, or measurement system used to define a particular scale.
  • D. scaleOptimizedFor
    Indicates that something has been adjusted or configured to operate most efficiently at a particular size, level, or magnitude.
  • E. scalingProperty
    Indicates how a quantity or behavior changes in proportion to changes in another variable, typically under resizing or rescaling conditions.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b3ffa548190a060d6e94562a5d2 completed April 20, 2026, 12:25 p.m.
PD Predicate disambiguation batch_69e4fd602f008190aa9bc76ae17e4ce1 completed April 19, 2026, 4:05 p.m.
Created at: April 10, 2026, 1:35 p.m.