Triple

T17568806
Position Surface form Disambiguated ID Type / Status
Subject AnyCancellable E427883 entity
Predicate lifecycleBehavior P128016 FINISHED
Object cancels subscription on deinit 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: cancels subscription on deinit | Statement: [AnyCancellable, lifecycleBehavior, cancels subscription on deinit]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: lifecycleBehavior
Context triple: [AnyCancellable, lifecycleBehavior, cancels subscription on deinit]
  • A. lifecycleType
    Indicates the specific stage or pattern within an entity’s overall lifecycle that characterizes how it begins, evolves, and ends.
  • B. lifecycleModel
    Indicates that one entity defines or follows the structured sequence of phases or stages governing the development, use, and retirement of another entity.
  • C. lifecycleFeature
    Indicates that one entity is a feature, phase, or characteristic associated with a particular stage in the lifecycle of another entity.
  • D. lifecycleTiedTo
    Indicates that the existence, duration, or validity of one entity is dependent on and ends with the lifecycle of another entity.
  • E. designedForLifecycle
    Indicates that something has been intentionally created or configured to support, align with, or optimize a particular lifecycle or set of lifecycle stages.
  • F. None of above. chosen

Provenance (4 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4592f29d08190bc3de905d35af849 completed April 19, 2026, 4:25 a.m.
PD Predicate disambiguation batch_69e3b4fd7d048190b54ee4c6155612a5 completed April 18, 2026, 4:44 p.m.
PDg Predicate description generation batch_69e3bbb50b448190a59dd4be33c76db7 completed April 18, 2026, 5:13 p.m.
Created at: April 10, 2026, 5:50 a.m.