Triple
T9761848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NSCoder |
E236687
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | NSKeyedArchiver |
E820439
|
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: NSKeyedArchiver | Statement: [NSCoder, relatedTo, NSKeyedArchiver]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NSKeyedArchiver Context triple: [NSCoder, relatedTo, NSKeyedArchiver]
-
A.
NSKeyedArchiver
chosen
NSKeyedArchiver is a Foundation framework class in Apple platforms that serializes Objective‑C and Swift objects into an archive format suitable for persistent storage or transmission.
-
B.
NSKeyedUnarchiver
NSKeyedUnarchiver is a Foundation framework class in Apple’s platforms used to decode and reconstruct objects from archives created by NSKeyedArchiver.
-
C.
NSCoding
NSCoding is an Objective-C protocol in Apple’s frameworks that defines methods for encoding and decoding objects so they can be serialized and later reconstructed.
-
D.
NSSecureCoding
NSSecureCoding is an Apple protocol that extends NSCoding to require secure, type-checked archiving and unarchiving of objects to prevent object substitution attacks.
-
E.
NSCoder
NSCoder is an abstract class in Apple’s Foundation framework that provides an interface for encoding and decoding objects and values for archiving and serialization.
- 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.