Triple

T11060065
Position Surface form Disambiguated ID Type / Status
Subject QGIS E261485 entity
Predicate supportsFileFormat P8463 FINISHED
Object GPKG 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: GPKG | Statement: [QGIS, supportsFileFormat, GPKG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GPKG
Context triple: [QGIS, supportsFileFormat, GPKG]
  • 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. KML
    KML (Keyhole Markup Language) is an XML-based file format used to display geographic data and annotations in mapping applications such as Google Earth and Google Maps.
  • C. 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.
  • D. WKT
    WKT (Well-Known Text) is a text-based markup language used to represent vector geometry objects such as points, lines, and polygons in geographic information systems.
  • E. 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.
  • 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_69e3c87ab0308190a6a6ada1708f0ec2 completed April 18, 2026, 6:07 p.m.
Created at: April 8, 2026, 9:26 p.m.