Triple

T32122952
Position Surface form Disambiguated ID Type / Status
Subject NSMutableCopying E820427 entity
Predicate usedInLanguageFeature P195456 FINISHED
Object id<NSMutableCopying> protocol-qualified types 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: id<NSMutableCopying> protocol-qualified types | Statement: [NSMutableCopying, usedInLanguageFeature, id<NSMutableCopying> protocol-qualified types]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usedInLanguageFeature
Context triple: [NSMutableCopying, usedInLanguageFeature, id<NSMutableCopying> protocol-qualified types]
  • A. usedInLanguage
    Indicates that something (such as a word, expression, or symbol) is employed or occurs within a particular language.
  • B. usedInSourceLanguageScript
    Indicates that a particular script is employed for writing in a given source language.
  • C. usedInType
    Indicates that something serves as a component, element, or example within a particular type or category.
  • D. usedInPattern
    Indicates that something serves as a component or element within a larger pattern or structured arrangement.
  • E. usedInMethod
    Indicates that something (such as a component, variable, or resource) is utilized or referenced within the execution or implementation of a particular method.
  • 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_69f34902d42c819083a8e6bba9a8bb9a completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69fdd2be648c8190b60b3d1caeb44364 completed May 8, 2026, 12:10 p.m.
PD Predicate disambiguation batch_69fdd14a5c708190a6f95ec61f4fc28f completed May 8, 2026, 12:04 p.m.
PDg Predicate description generation batch_69fdd2bda90881909aa229194d014ba7 completed May 8, 2026, 12:10 p.m.
Created at: May 1, 2026, 12:28 a.m.