Triple
T6716550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nabataean Aramaic |
E153282
|
entity |
| Predicate | writingCulture |
P11605
|
FINISHED |
| Object | epigraphic culture |
—
|
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: epigraphic culture | Statement: [Nabataean Aramaic, writingCulture, epigraphic culture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writingCulture Context triple: [Nabataean Aramaic, writingCulture, epigraphic culture]
-
A.
writtenByCulture
Indicates that something (such as a text, work, or artifact) is authored, created, or produced by a particular culture or cultural group.
-
B.
writingTradition
chosen
Indicates a relationship where an entity is associated with, follows, or belongs to a particular system or style of written expression or script usage.
-
C.
writingComponent
Indicates that one entity is a written part or element that contributes to the composition or structure of another entity.
-
D.
writingForm
Indicates the specific script, notation, or written representation used to express a piece of language or content.
-
E.
writesLanguage
Indicates that an entity produces written content in a particular language.
- 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_69c68809b4608190a2509ddb5ab87f05 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d125db3c8190aad28919226a16da |
completed | March 27, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69c6d08c5d348190a29dee668c398e70 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:07 p.m.