Triple
T7033176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AI (file format) |
E163316
|
entity |
| Predicate | canBeSavedAs |
P74584
|
FINISHED |
| Object | PDF-compatible AI file |
—
|
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: PDF-compatible AI file | Statement: [AI (file format), canBeSavedAs, PDF-compatible AI file]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeSavedAs Context triple: [AI (file format), canBeSavedAs, PDF-compatible AI file]
-
A.
isExportable
Indicates that something can be legally and practically transferred or sent out from one jurisdiction, system, or context to another.
-
B.
supportsSavingToCameraRoll
Indicates whether an action or feature allows content to be saved directly to the device’s camera roll.
-
C.
canBeShared
Indicates that something is capable of being distributed or accessed by multiple parties.
-
D.
canBeWrittenIn
Indicates that something is capable of being expressed, encoded, or represented using a particular language, notation, or medium.
-
E.
canBeDepictedAs
Indicates that one entity is capable of being visually represented or illustrated in the form or style of another entity.
- 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_69c6885d691c81908cf7d31083113886 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e458ad9c81908c3f492b317ce291 |
completed | March 27, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69c6e1b9a2488190aea351d96afa5a12 |
completed | March 27, 2026, 7:59 p.m. |
| PDg | Predicate description generation | batch_69c6e456e89481908df42a1b4232a4a0 |
completed | March 27, 2026, 8:11 p.m. |
Created at: March 27, 2026, 2:36 p.m.