Triple
T18994626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NC 96 |
E464777
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | US 1 |
—
|
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: US 1 | Statement: [NC 96, connectsTo, US 1]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: US 1 Context triple: [NC 96, connectsTo, US 1]
-
A.
US 1
chosen
US 1 is a major north–south U.S. highway running along the East Coast, serving as a key route through numerous states and cities from Florida to Maine.
-
B.
US 2
US 2 is a major east–west U.S. highway that runs across the northern United States, roughly parallel to the Canadian border.
-
C.
US 4
US 4 is a U.S. highway in the northeastern United States that runs east–west through New York, Vermont, and New Hampshire, connecting several regional cities and interstate routes.
-
D.
US 7
US 7 is a north–south U.S. highway in New England that runs from Connecticut through Massachusetts to Vermont, serving as a major regional route.
-
E.
US 1/9
US 1/9 is a concurrent section of U.S. Routes 1 and 9 that runs through northern New Jersey, serving as a major urban arterial and connector to routes into New York City.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d680dd2881908a72e732c6b25477 |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.