Triple

T30503580
Position Surface form Disambiguated ID Type / Status
Subject AltaGas Ltd. E776203 entity
Predicate hasExportFocus P63716 FINISHED
Object liquefied petroleum gas exports 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: liquefied petroleum gas exports | Statement: [AltaGas Ltd., hasExportFocus, liquefied petroleum gas exports]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasExportFocus
Context triple: [AltaGas Ltd., hasExportFocus, liquefied petroleum gas exports]
  • A. hasVisualFocus
    Indicates that one entity is currently directing its visual attention or gaze toward another entity.
  • B. hasPrimaryFocus
    Indicates that something is the main subject, concern, or area of attention for an entity or activity.
  • C. hasGlobalFocus chosen
    Indicates that something is oriented toward, concerned with, or applicable to worldwide or international scope rather than a local or regional one.
  • D. hasActingFocus
    Indicates that an entity is the primary performer or focal agent carrying out an action in a given context.
  • E. hasAccessibilityFocus
    Indicates that a user interface element is currently the primary target of accessibility tools, such as screen readers or keyboard navigation, receiving focused attention for interaction.
  • 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_69f22498c5d481908aaea89e6fab8280 completed April 29, 2026, 3:32 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, 8:15 p.m.