Triple

T10330170
Position Surface form Disambiguated ID Type / Status
Subject CityGML E242852 entity
Predicate abbreviation P43 FINISHED
Object CityGML E242852 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: CityGML | Statement: [CityGML, abbreviation, CityGML]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CityGML
Context triple: [CityGML, abbreviation, CityGML]
  • A. CityGML chosen
    CityGML is an open data model and XML-based format for storing and exchanging 3D city and landscape models, widely used in urban planning, simulation, and geographic information systems.
  • B. SensorML
    SensorML is an Open Geospatial Consortium standard XML-based language for describing sensors, sensor systems, and their processes to enable discovery, interoperability, and use in geospatial and sensor web applications.
  • C. ONS Open Geography portal
    The ONS Open Geography portal is an online platform providing access to official UK geographic data, boundaries, and related statistical geospatial resources published by the Office for National Statistics.
  • D. GeoSPARQL
    GeoSPARQL is an Open Geospatial Consortium standard that extends SPARQL to support querying and representing geospatial data on the Semantic Web.
  • E. Geography Markup Language
    Geography Markup Language is an XML-based standard developed by the Open Geospatial Consortium for modeling, storing, and exchanging geographic information and spatial features.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7fb77348190ac8ff887f6f03450 completed April 7, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d794f3a130819095a8befd8fa3a9f0 completed April 9, 2026, noon
Created at: April 6, 2026, 11:52 a.m.