Triple
T17876163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colorado State Highway system |
E446959
|
entity |
| Predicate | routeMarkerShape |
P20601
|
FINISHED |
| Object | square |
—
|
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: square | Statement: [Colorado State Highway system, routeMarkerShape, square]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routeMarkerShape Context triple: [Colorado State Highway system, routeMarkerShape, square]
-
A.
routeSymbolShape
chosen
Indicates the specific geometric form or outline used to depict a route’s symbol in a visual or cartographic representation.
-
B.
mapSymbolStandard
Indicates that a map symbol conforms to, or is defined according to, a particular cartographic standard or specification.
-
C.
mapSymbol
Indicates a correspondence where one symbol is used to represent, stand for, or denote another element within a mapping or representation system.
-
D.
iconShape
Indicates the geometric form or outline that an icon visually takes.
-
E.
mapShape
Indicates a correspondence between an original shape and its transformed or represented version in another space, system, or context.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa614b48190bdc9e905e9e6d5e0 |
completed | April 19, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e6d2e88190ad9ef9f8a99f13e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:18 a.m.