Triple
T27296059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Interstate 990 |
E688766
|
entity |
| Predicate | isAuxiliaryRouteOf |
P130931
|
FINISHED |
| Object | Interstate 90 |
—
|
NE NERFINISHED |
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: Interstate 90 | Statement: [Interstate 990, isAuxiliaryRouteOf, Interstate 90]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAuxiliaryRouteOf Context triple: [Interstate 990, isAuxiliaryRouteOf, Interstate 90]
-
A.
isRelatedRouteOf
chosen
Indicates that one route is connected to, associated with, or serves as an alternative or complementary path to another route.
-
B.
isPrincipalRouteOf
Indicates that one route serves as the main or primary route associated with another route or network.
-
C.
isRadialRouteOf
Indicates that one route functions as a radial connection extending outward from a central point, hub, or main route.
-
D.
servesAsRouteTo
Indicates that one entity functions as a pathway, channel, or means of access leading to another entity.
-
E.
isPartOfRoute
Indicates that something (such as a segment, stop, or step) belongs to and is contained within a larger route.
- 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_69ef355a96308190a2bed991525fb278 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f6277ff9848190958c203e511b1393 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:18 a.m.