Triple
T7327869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sogdian alphabet |
E168919
|
entity |
| Predicate | writingDirectionType |
P2264
|
FINISHED |
| Object | horizontal |
—
|
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: horizontal | Statement: [Sogdian alphabet, writingDirectionType, horizontal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writingDirectionType Context triple: [Sogdian alphabet, writingDirectionType, horizontal]
-
A.
hasWritingDirection
chosen
Indicates the direction in which writing or text is read or written for a given script, language, or text system.
-
B.
translationDirection
Indicates the source and target languages involved in a translation, specifying the direction from the original language to the translated language.
-
C.
writingSystem
Indicates that one entity is the script or system of written symbols used to represent the language or content of another entity.
-
D.
writesLanguage
Indicates that an entity produces written content in a particular language.
-
E.
writingSystemUsedIn
Indicates that a particular writing system is employed for written communication within a given language, region, or context.
- 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_69c68a54cacc81908e3b773441f19566 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0a879b88190bef0fb6cbae411ff |
completed | March 27, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69c6e77230048190b2c29ca6b3a65b8e |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:03 p.m.