Triple
T2578103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bancor |
E57023
|
entity |
| Predicate | unitRole |
P40371
|
FINISHED |
| Object | international reserve asset |
—
|
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: international reserve asset | Statement: [Bancor, unitRole, international reserve asset]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unitRole Context triple: [Bancor, unitRole, international reserve asset]
-
A.
typeOfRole
Indicates that one entity specifies the kind or category of role that another entity holds or performs.
-
B.
definesRole
Indicates that one entity specifies or establishes the role, function, or position of another entity within a given context.
-
C.
servesRole
Indicates that one entity performs, fulfills, or occupies a particular function, position, or responsibility in relation to another entity.
-
D.
allianceRole
Indicates the specific function, status, or responsibility an entity holds within an alliance or cooperative partnership.
-
E.
identificationRole
Indicates that an entity serves as an identifier or plays a role in uniquely distinguishing or recognizing another entity.
- 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_69ab4a4dca6481908c301f8e317396e7 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd3a86f9881908df29a7caaf9a7df |
completed | March 7, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69abd0cfeae08190aed03866ba071c5c |
completed | March 7, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69abd209d934819093600889af9104c3 |
completed | March 7, 2026, 7:21 a.m. |
Created at: March 6, 2026, 9:49 p.m.