Triple
T18431135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alabama State Route 10 |
E450269
|
entity |
| Predicate | isSignedAs |
P9766
|
FINISHED |
| Object | SR 10 |
—
|
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: SR 10 | Statement: [Alabama State Route 10, isSignedAs, SR 10]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SR 10 Context triple: [Alabama State Route 10, isSignedAs, SR 10]
-
A.
SR 10
chosen
SR 10 is a designation used for a major east–west state highway corridor in Florida that includes portions of several well-known routes such as U.S. Highway 90.
-
B.
SR 101
SR 101, commonly known as Loop 101, is a major beltway freeway serving the Phoenix metropolitan area in Arizona.
-
C.
SR 110
SR 110 is a state highway designation used for a specific numbered route within a U.S. state's road network.
-
D.
SR 102
SR 102 is a state highway in Maine that runs through Mount Desert Island, providing access to Acadia National Park and several coastal communities.
-
E.
SR 11
SR 11 is a planned and partially completed state highway intended to serve as a transportation corridor within its state’s road network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d381d6388190a9e94e9c658174e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e51b1771788190b26afdf65e9de502 |
completed | April 19, 2026, 6:12 p.m. |
Created at: April 10, 2026, 11:26 a.m.