Triple
T4348916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosetta Stone |
E97972
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | multilingual inscription |
C15764
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: multilingual inscription Context triple: [Rosetta Stone, instanceOf, multilingual inscription]
-
A.
Latin inscription
A Latin inscription is a text carved, engraved, or otherwise permanently marked in the Latin language on durable materials such as stone, metal, or pottery, typically serving commemorative, dedicatory, legal, or informational purposes.
-
B.
inscription corpus
An inscription corpus is a systematically collected and organized body of inscribed texts (such as carvings on stone, metal, or other durable materials) used for linguistic, historical, and archaeological analysis.
-
C.
epigraphic language
An epigraphic language is a language known primarily or exclusively from inscriptions carved or written on durable materials such as stone, metal, or pottery, rather than from extensive literary or manuscript traditions.
-
D.
Etruscan inscription
An Etruscan inscription is a text written in the ancient Etruscan language, typically carved or painted on durable materials such as stone, metal, or pottery, providing evidence of the culture, religion, and daily life of the Etruscan civilization.
-
E.
ancient Javanese inscription
An ancient Javanese inscription is a historical text carved or written in Old Javanese script on durable materials such as stone, metal, or clay, documenting religious, political, legal, or cultural aspects of early Javanese civilization.
- F. None of above. chosen
Provenance (1 batch)
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_69b34548402c819085ab68b27c235a87 |
completed | March 12, 2026, 10:59 p.m. |
Created at: March 12, 2026, 11:15 p.m.