Triple

T9761721
Position Surface form Disambiguated ID Type / Status
Subject NSDate E236685 entity
Predicate superclass P2372 FINISHED
Object NSObject E236681 NE 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: NSObject | Statement: [NSDate, superclass, NSObject]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NSObject
Context triple: [NSDate, superclass, NSObject]
  • A. NSObject chosen
    NSObject is the root base class in Objective-C from which most classes in Cocoa and Cocoa Touch inherit, providing fundamental object behavior such as memory management and message sending.
  • B. Objective-C
    Objective-C is an object-oriented programming language primarily known for its use in developing software for Apple's macOS and iOS platforms.
  • C. ZObject
    ZObject is the fundamental data structure used in WikiLambda to represent and store functions, data, and other entities in a language-independent, structured format.
  • D. OPENSTEP
    OPENSTEP is an object-oriented application programming interface and operating system environment developed by NeXT that later formed the technological foundation for macOS and iOS.
  • E. Cocoa Touch
    Cocoa Touch is Apple’s application development framework for building iOS and other mobile OS apps, providing the UI components, event handling, and infrastructure layers on top of the underlying operating system.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca84d64f6c8190a4ed4e9f5936eda5 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda04c70108190a8ed09eb6f2a124e completed April 1, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5a4a88c8190bac0a2bff02804dc completed April 5, 2026, 3:23 a.m.
Created at: March 30, 2026, 8:25 p.m.