Triple
T34874266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Route 321 in South Carolina |
E1005834
|
entity |
| Predicate | stateBorderTerminus |
P93185
|
FINISHED |
| Object | Georgia–South Carolina border |
—
|
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: Georgia–South Carolina border | Statement: [U.S. Route 321 in South Carolina, stateBorderTerminus, Georgia–South Carolina border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateBorderTerminus Context triple: [U.S. Route 321 in South Carolina, stateBorderTerminus, Georgia–South Carolina border]
-
A.
borderTerminus
chosen
Indicates the endpoint location where a border between two areas or entities begins or ends.
-
B.
stateBorderContext
Indicates that one state shares a border with another state within a specified geographic or political context.
-
C.
borderingStateOrTerritory
Indicates that one state or territory shares a common boundary with another state or territory.
-
D.
borderingStateOrProvince
Indicates that one state or province shares a common boundary with another state or province.
-
E.
borderStateOf
Indicates that one state shares a common boundary or border with another state.
- F. None of above.
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_69f76dbde1c08190a24e7f9beb564c8d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe96c2647c819082989f11e1ae3d35 |
completed | May 9, 2026, 2:06 a.m. |
| PD | Predicate disambiguation | batch_69fe928615448190af939e5a94be55bb |
completed | May 9, 2026, 1:48 a.m. |
Created at: May 3, 2026, 4 p.m.