Triple
T844707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Route 75 |
E18251
|
entity |
| Predicate | connectsWith |
P37
|
FINISHED |
| Object | Interstate 45 |
E17695
|
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: Interstate 45 | Statement: [U.S. Route 75, connectsWith, Interstate 45]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Interstate 45 Context triple: [U.S. Route 75, connectsWith, Interstate 45]
-
A.
Interstate 45
chosen
Interstate 45 is a major north–south U.S. highway in Texas that connects the cities of Dallas and Houston.
-
B.
Interstate 49
Interstate 49 is a major north–south U.S. Interstate Highway running through multiple states in the central United States, including Missouri.
-
C.
Interstate 55
Interstate 55 is a major north–south U.S. highway running from Louisiana to Illinois, connecting cities such as New Orleans, Memphis, and Chicago.
-
D.
Interstate 459
Interstate 459 is a bypass loop around Birmingham, Alabama, that helps divert traffic from the city’s main interstate corridors.
-
E.
U.S. Route 45
U.S. Route 45 is a major north–south United States highway that runs from the Gulf Coast in Mississippi through several Midwestern states to the Upper Peninsula of Michigan.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac09249c8190a8099b94a3c9e2cc |
completed | March 1, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae890a2a0c8190a83cda5f037763bd |
completed | March 9, 2026, 8:47 a.m. |
Created at: March 1, 2026, 7:38 p.m.