Triple

T9761682
Position Surface form Disambiguated ID Type / Status
Subject NSData E236684 entity
Predicate introducedIn P513 FINISHED
Object Cocoa API E59592 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: Cocoa API | Statement: [NSData, introducedIn, Cocoa API]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cocoa API
Context triple: [NSData, introducedIn, Cocoa API]
  • A. macOS Cocoa chosen
    macOS Cocoa is Apple’s native object-oriented application framework for building graphical user interfaces on macOS.
  • B. 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.
  • C. Gluon API
    Gluon API is a high-level, imperative deep learning interface designed for building and training neural networks more easily and flexibly on the Apache MXNet framework.
  • D. Pascal API
    Pascal API is a Pascal-based application programming interface used for developing and integrating software components in Pascal.
  • E. Symbol API
    Symbol API is MXNet’s symbolic computation interface for defining, composing, and optimizing deep learning models as static computation graphs.
  • 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_69d1c41022908190a5f55291a2323691 completed April 5, 2026, 2:08 a.m.
Created at: March 30, 2026, 8:25 p.m.