Triple
T17560919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WKB |
E427693
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | SpatiaLite |
—
|
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: SpatiaLite | Statement: [WKB, usedBy, SpatiaLite]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SpatiaLite Context triple: [WKB, usedBy, SpatiaLite]
-
A.
SpatiaLite
chosen
SpatiaLite is an open-source spatial extension to the SQLite database engine that adds support for storing and querying geospatial data.
-
B.
cuSpatial
cuSpatial is a GPU-accelerated spatial and GIS analytics library within NVIDIA RAPIDS designed to perform high-performance geospatial data processing.
-
C.
PostGIS
PostGIS is an open-source spatial database extender that adds robust geographic object support and spatial querying capabilities to PostgreSQL.
-
D.
Oracle Spatial
Oracle Spatial is an extension to the Oracle Database that provides advanced spatial data storage, indexing, and analysis capabilities for geographic information systems and location-based applications.
-
E.
GeoPackage
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.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e456267e208190a1238fbe1a535bb0 |
completed | April 19, 2026, 4:12 a.m. |
Created at: April 10, 2026, 5:50 a.m.