Triple
T18268021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buffalo nickel |
E437533
|
entity |
| Predicate | reverseSubject |
P9300
|
FINISHED |
| Object | American bison (often called buffalo) |
—
|
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: American bison (often called buffalo) | Statement: [Buffalo nickel, reverseSubject, American bison (often called buffalo)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reverseSubject Context triple: [Buffalo nickel, reverseSubject, American bison (often called buffalo)]
-
A.
reverseDesignSubject
Indicates that the subject is the entity for which a design or plan is derived by reversing or backtracking from an existing outcome or artifact.
-
B.
reversed
chosen
Indicates that the direction or order of a previously defined relationship or sequence between entities is inverted.
-
C.
reverseFeature
Indicates that one feature is the inverse or opposite counterpart of another feature in a given context.
-
D.
alsoReveres
Indicates that one entity holds reverence or deep respect for something or someone that another entity also reveres.
-
E.
typicalReverseType
Indicates that the subject is the usual or canonical inverse relation type of the given predicate.
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ff7bda5c8190a5a85f3cfb7aa4ef |
completed | April 19, 2026, 4:14 p.m. |
| PD | Predicate disambiguation | batch_69e44fd81c788190b08c6be3b07a08c5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:34 a.m.