Triple
T27189390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maryland Route 17 |
E683427
|
entity |
| Predicate | connectsToUSRoute |
P39744
|
FINISHED |
| Object | U.S. Route 40 |
—
|
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: U.S. Route 40 | Statement: [Maryland Route 17, connectsToUSRoute, U.S. Route 40]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsToUSRoute Context triple: [Maryland Route 17, connectsToUSRoute, U.S. Route 40]
-
A.
servedByU.S.Route
chosen
Indicates that a place or transportation feature is provided access or connectivity by a specific U.S. Route highway.
-
B.
connectsInlandRoutesTo
Indicates that one entity serves as a link or junction that enables inland transportation routes to reach or connect with another entity.
-
C.
connectsToInterstate
Indicates that one roadway, route, or location has a direct connection or access point to an interstate highway.
-
D.
connectsNorthTo
Indicates that one entity serves as a connection or link from another entity to something located to its north.
-
E.
stateRouteConnection
Indicates a relationship where a state-level route connects or links two locations or transportation segments.
- 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_69eefad140408190b8586fdebcf9af46 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: April 27, 2026, 9:31 a.m.