Triple
T34955028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SumatraPDF |
E1008102
|
entity |
| Predicate | softwareVersioning |
P5326
|
FINISHED |
| Object | stable release model |
—
|
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: stable release model | Statement: [SumatraPDF, softwareVersioning, stable release model]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softwareVersioning Context triple: [SumatraPDF, softwareVersioning, stable release model]
-
A.
versionFormat
Indicates the specific structural pattern or notation used to represent a version identifier.
-
B.
versionComponent
Indicates that one entity is a component or segment of another entity’s version identifier (e.g., major, minor, or patch number).
-
C.
versioningModel
chosen
Indicates that one entity serves as a versioning or revision-control model governing how versions of another entity are created, tracked, and managed.
-
D.
versionOf
Indicates that one entity is a specific form, edition, or variant derived from or corresponding to another entity.
-
E.
versioningRule
Indicates the rule or policy that governs how different versions of an entity are created, labeled, and managed over time.
- 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_69f76dc69564819099e9e78aed6ff0a6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4 p.m.