Triple
T17842585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apollodotus I |
E445568
|
entity |
| Predicate | coinMetal |
P73799
|
FINISHED |
| Object | silver |
—
|
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: silver | Statement: [Apollodotus I, coinMetal, silver]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coinMetal Context triple: [Apollodotus I, coinMetal, silver]
-
A.
authorizedCoinMetal
Indicates that a particular metal is officially approved for use in minting a given coin.
-
B.
coinageType
Indicates the specific type or category of coinage associated with an entity, such as its denomination, series, or monetary classification.
-
C.
mediumOfCoinage
chosen
Indicates the material or substance used as the physical medium in which a coin or form of money is produced.
-
D.
nobleMetal
Indicates that the subject is classified as a noble (chemically inert and corrosion-resistant) metal.
-
E.
associatedMetal
Indicates a relationship where one entity is linked or connected to a particular metal, such as by composition, usage, origin, or symbolic association.
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d2c3fa8819089bfbeb807a25376 |
completed | April 19, 2026, 8:07 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e266888190ae976b4b7d5b886f |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:16 a.m.