Triple
T29207349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cypro-Minoan script |
E740449
|
entity |
| Predicate | mainWritingMedium |
P48838
|
FINISHED |
| Object | clay tablets |
—
|
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: clay tablets | Statement: [Cypro-Minoan script, mainWritingMedium, clay tablets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainWritingMedium Context triple: [Cypro-Minoan script, mainWritingMedium, clay tablets]
-
A.
editingMedium
Indicates the medium or format through which an editing action is performed or realized.
-
B.
manuscriptMedium
chosen
Indicates the material or physical medium on which a manuscript is written or produced.
-
C.
writesForMedium
Indicates that one entity creates written content intended for publication on a particular medium or platform.
-
D.
writingMediumModern
Indicates that the writing activity is carried out using a modern medium or tool (such as digital or contemporary writing instruments) rather than traditional ones.
-
E.
currentlyWrittenIn
Indicates that a work or document is, at the present time, expressed or composed in a particular language or writing system.
- 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_69f07cb974108190b7e86ca489a6ebb6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f66402f5348190be752c897f8e5e2d |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 12:09 p.m.