Triple
T11060137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | QGIS |
E261485
|
entity |
| Predicate | supportsVectorFormat |
P97573
|
FINISHED |
| Object | GeoPackage |
E856256
|
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: GeoPackage | Statement: [QGIS, supportsVectorFormat, GeoPackage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GeoPackage Context triple: [QGIS, supportsVectorFormat, GeoPackage]
-
A.
GeoPackage
chosen
GeoPackage is an open, platform-independent, SQLite-based format for storing and exchanging geospatial data such as vector features, tile matrices, and metadata in a single file.
-
B.
SpatiaLite
SpatiaLite is an open-source spatial extension to the SQLite database engine that adds support for storing and querying geospatial data.
-
C.
GDAL
GDAL is an open-source geospatial data abstraction library widely used for reading, writing, and transforming a broad range of raster and vector geographic data formats.
-
D.
GeoJSON
GeoJSON is a widely used JSON-based format for encoding a variety of geographic data structures, including points, lines, polygons, and their associated attributes.
-
E.
PostGIS
PostGIS is an open-source spatial database extender that adds robust geographic object support and spatial querying capabilities to PostgreSQL.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798e991848190b07c2f48dae38681 |
completed | April 9, 2026, 12:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3e75b90ec8190b1a799e0183c6784 |
completed | April 18, 2026, 8:19 p.m. |
Created at: April 8, 2026, 9:26 p.m.