Triple
T23982703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | global trade coin |
E604548
|
entity |
| Predicate | mayBeMaterializedAs |
P93459
|
FINISHED |
| Object | gold coins |
—
|
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: gold coins | Statement: [global trade coin, mayBeMaterializedAs, gold coins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBeMaterializedAs Context triple: [global trade coin, mayBeMaterializedAs, gold coins]
-
A.
mayBeCached
Indicates that the result of an operation or data retrieval is allowed to be stored for potential reuse in a cache.
-
B.
canBeLinearizedAs
Indicates that one entity can be represented or transformed into an equivalent linear (ordered or sequential) form as the other entity.
-
C.
canBeVirtualized
Indicates that an entity is capable of being run or represented within a virtualized environment rather than directly on physical hardware.
-
D.
mayBeFormedWhen
chosen
Indicates that one entity has the potential to come into existence or be created as a result of another entity, condition, or process.
-
E.
mayBeUpgradedTo
Indicates that one entity is eligible or allowed to be changed into a higher, improved, or more advanced version represented by another 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_69e29543f40c819087700b7a272afb60 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d2bf02fc8190bebd59f149e0bbfc |
completed | April 29, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:29 p.m.