Triple
T3786092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cotton gin |
E85533
|
entity |
| Predicate | patentType |
P3855
|
FINISHED |
| Object | United States patent |
—
|
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: United States patent | Statement: [cotton gin, patentType, United States patent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patentType Context triple: [cotton gin, patentType, United States patent]
-
A.
patent
Indicates that a legal protection has been granted to an entity for an invention, giving it exclusive rights to make, use, or sell that invention.
-
B.
inventionType
Indicates the specific category or kind of invention that characterizes the relationship between an invention and its type.
-
C.
patentIn
chosen
Indicates that one entity holds or is associated with a patent located, filed, or registered in a particular jurisdiction, organization, or context represented by the other entity.
-
D.
typeOfPatentsGranted
Indicates the specific categories or kinds of patents that have been officially granted to an entity.
-
E.
patentNumber
Indicates that a specific patent is identified or referenced by a particular patent number.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee634c6ac819099653c660c286746 |
completed | March 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69aee3d3c92c819081d9d5c45ef37a5d |
completed | March 9, 2026, 3:14 p.m. |
Created at: March 9, 2026, 3:13 p.m.