Triple
T14679901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Route 37 (California) |
E344749
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | SR 37 |
E859844
|
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 37 | Statement: [State Route 37 (California), alsoKnownAs, SR 37]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SR 37 Context triple: [State Route 37 (California), alsoKnownAs, SR 37]
-
A.
SR 37
chosen
SR 37 is a state highway in Northern California that runs along the northern edge of San Pablo Bay, connecting U.S. Route 101 in Marin County to Interstate 80 in Solano County.
-
B.
SR 37
SR 37 is a state highway in Ohio that runs east–west across the central part of the state, connecting several communities and intersecting multiple major routes.
-
C.
SR 38
SR 38 is a California state highway that runs through the San Bernardino Mountains, providing scenic access between the Inland Empire and the Big Bear Lake area.
-
D.
SR 38
SR 38 is a state highway in Georgia that runs east–west across the southern part of the state, connecting several cities and major routes.
-
E.
SR 31
SR 31 is a state highway in northeastern Washington that runs north–south from near the town of Metaline Falls to the Canadian border.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb5692284819090f775be8e478522 |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde180ff0c8190a8b7c7804e36c3f8 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:27 a.m.