Triple
T18190127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oklahoma state highway system |
E435509
|
entity |
| Predicate | routeMarkerText |
P75208
|
FINISHED |
| Object | OK |
—
|
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: OK | Statement: [Oklahoma state highway system, routeMarkerText, OK]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routeMarkerText Context triple: [Oklahoma state highway system, routeMarkerText, OK]
-
A.
routeSymbolShape
Indicates the specific geometric form or outline used to depict a route’s symbol in a visual or cartographic representation.
-
B.
signpostFeature
Indicates that one entity serves as a signpost-related feature or element associated with another entity.
-
C.
notableRouteFeature
Indicates that a route is associated with a distinctive or significant feature, such as a landmark, characteristic terrain, or other notable aspect along its path.
-
D.
routeSymbol
chosen
Indicates that a particular symbol or code is used to represent or identify a specific route.
-
E.
routeDescription
Indicates a textual explanation or summary of the path, course, or itinerary taken between locations.
- 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0016ec08190ae853dbc89865a41 |
completed | April 19, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69e4331e92408190ad607ba4956a3897 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:31 a.m.