Triple
T13282081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Route 108 |
E316346
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | SR 108 |
E466510
|
NE 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: SR 108 | Statement: [State Route 108, abbreviation, SR 108]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SR 108 Context triple: [State Route 108, abbreviation, SR 108]
-
A.
SR 108
chosen
SR 108 is a California state highway that traverses the Sierra Nevada, including the high-altitude Sonora Pass, connecting the Central Valley with the eastern side of the range.
-
B.
SR 109
SR 109 is a state highway in Maine that connects the coastal city of Wells with inland communities, serving as a regional route for local and through traffic.
-
C.
SR 180
SR 180 is a state highway designation used for specific numbered routes 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 188
SR 188 is a state highway in Ohio that connects several communities in the central part of the state.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d806b349908190a9a61dd9323bf153 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9904507588190a303686d176ec3e1 |
completed | April 11, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f739760f748190ace82b1f3c8ce204 |
completed | May 3, 2026, 12:03 p.m. |
Created at: April 9, 2026, 9:27 p.m.