Triple
T19508361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ordnance Survey Explorer maps |
E488084
|
entity |
| Predicate | typicalSheetCoverage |
P41336
|
FINISHED |
| Object | local area |
—
|
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: local area | Statement: [Ordnance Survey Explorer maps, typicalSheetCoverage, local area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSheetCoverage Context triple: [Ordnance Survey Explorer maps, typicalSheetCoverage, local area]
-
A.
stageCoverage
Indicates that one entity provides or has coverage, representation, or support for another within a particular stage or phase of a process or workflow.
-
B.
surfaceCover
Indicates that one entity forms the material or layer that covers the outer surface of another entity.
-
C.
edgeCoverage
Indicates that one element (such as a test, path, or configuration) covers or exercises a specific edge or connection in a graph or network structure.
-
D.
typicallyCovers
chosen
Indicates that one entity is the kind of thing that usually or normally includes, addresses, or encompasses another entity.
-
E.
screenCoverage
Indicates the extent to which one entity visually occupies or covers the display area of another (e.g., how much of a screen is taken up by a given element).
- 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6351426448190aec1ee26c09faa24 |
completed | April 20, 2026, 2:15 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7bd25881908caa04eaef1f6718 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:40 p.m.