Triple
T7252152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cyrus McCormick |
E157627
|
entity |
| Predicate | patentGrantedFor |
P49345
|
FINISHED |
| Object | mechanical reaper |
—
|
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: mechanical reaper | Statement: [Cyrus McCormick, patentGrantedFor, mechanical reaper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patentGrantedFor Context triple: [Cyrus McCormick, patentGrantedFor, mechanical reaper]
-
A.
hasPatentGrant
chosen
Indicates that a patent grant exists conferring legal protection or rights to an entity for a specific invention or intellectual property.
-
B.
grantedRoyalPatentBy
Indicates that an entity has been formally given a royal patent by a specified royal authority or monarch.
-
C.
typeOfPatentsGranted
Indicates the specific categories or kinds of patents that have been officially granted to an entity.
-
D.
patentStatus
Indicates the legal protection state of an invention or intellectual property, such as whether it is patented, pending, expired, or not filed.
-
E.
patentIn
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.
- 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_69c6882d81d4819085f7ff862951ee4f |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea7ae0e48190bd80c91bad1976c6 |
completed | March 27, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69c6e7666ffc81908bf643d8257e6337 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:56 p.m.