Triple
T28063066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows Installer package |
E709166
|
entity |
| Predicate | standardFileNameExtensionFor |
P105373
|
FINISHED |
| Object | Windows Installer database |
—
|
NE NERFINISHED |
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: Windows Installer database | Statement: [Windows Installer package, standardFileNameExtensionFor, Windows Installer database]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standardFileNameExtensionFor Context triple: [Windows Installer package, standardFileNameExtensionFor, Windows Installer database]
-
A.
containerFilenameExtension
Indicates that one item is a filename extension associated with a particular container format.
-
B.
filenameType
Indicates the type or category associated with a given filename (e.g., file format, role, or classification).
-
C.
typicalFileFormat
chosen
Indicates the usual or standard file format typically associated with or used for a given entity or context.
-
D.
fileExtensionForGadgets
Indicates the file extension that is associated with or used by a given gadget.
-
E.
introducedFileExtension
Indicates that an entity caused a particular file extension to be created, defined, or brought into use.
- 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_69ef9b6eb6d88190a3fea236eb0f7bed |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b78f29481908cc8f390496dee97 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 27, 2026, 8:41 p.m.