Triple
T32150088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NSUnarchiver |
E821133
|
entity |
| Predicate | canUnarchiveDataFrom |
P104004
|
FINISHED |
| Object | NSArchiver archives |
—
|
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: NSArchiver archives | Statement: [NSUnarchiver, canUnarchiveDataFrom, NSArchiver archives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canUnarchiveDataFrom Context triple: [NSUnarchiver, canUnarchiveDataFrom, NSArchiver archives]
-
A.
archiveOf
Indicates that one entity serves as a stored collection or repository preserving the records, documents, or materials of another entity.
-
B.
archiveAvailability
Indicates whether something is stored or accessible in an archive, and under what conditions it can be retrieved.
-
C.
archiveFor
Indicates that one entity serves as a storage or preservation repository specifically for the records, documents, or data of another entity.
-
D.
canExtractTo
Indicates that one entity is capable of being extracted, converted, or exported into another specified format, location, or representation.
-
E.
canExtract
chosen
Indicates that one entity has the ability or permission to extract or derive something from another entity or source.
- F. None of above.
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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b9e7cb088190926d6a5c524e5eab |
completed | May 3, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a970b0819090c6473844ffa8e3 |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:31 a.m.