Triple
T26121668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roanoke Rapids Dam |
E658986
|
entity |
| Predicate | FERCLicenseType |
P159973
|
FINISHED |
| Object | hydropower license |
—
|
LITERAL 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: hydropower license | Statement: [Roanoke Rapids Dam, FERCLicenseType, hydropower license]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FERCLicenseType Context triple: [Roanoke Rapids Dam, FERCLicenseType, hydropower license]
-
A.
FERCLicenseHolder
Indicates that an entity holds or is registered as the holder of a license issued by the Federal Energy Regulatory Commission (FERC).
-
B.
fccLicensingAuthority
Indicates that an entity serves as the licensing authority recognized or regulated by the U.S. Federal Communications Commission (FCC) for another entity or regulated item.
-
C.
licenseFamily
Indicates that one license belongs to, is derived from, or is categorized under a broader family or class of related licenses.
-
D.
licenseFocus
Indicates that a license specifically targets, applies to, or is primarily concerned with a particular subject, activity, or scope.
-
E.
licenseListType
Indicates the specific category or type of license list to which an item or license entry belongs.
- F. None of above. chosen
Provenance (4 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_69ee5bc2b2948190b458ad3f580af779 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60acc421481909c02cdbfcc5754a4 |
completed | May 2, 2026, 2:31 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
| PDg | Predicate description generation | batch_69f5f6b32a8881909baa0db57b80d56a |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 26, 2026, 8:09 p.m.