Triple
T21593699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flag of Saudi Arabia |
E532842
|
entity |
| Predicate | textDirection |
P2264
|
FINISHED |
| Object | right-to-left |
—
|
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: right-to-left | Statement: [Flag of Saudi Arabia, textDirection, right-to-left]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: textDirection Context triple: [Flag of Saudi Arabia, textDirection, right-to-left]
-
A.
translationDirection
Indicates the source and target languages involved in a translation, specifying the direction from the original language to the translated language.
-
B.
hasWritingDirection
chosen
Indicates the direction in which writing or text is read or written for a given script, language, or text system.
-
C.
textAlignment
Indicates how text is positioned or aligned relative to a reference frame, such as margins, columns, or other layout boundaries.
-
D.
textMode
Indicates that something operates, is displayed, or is processed in a mode where information is handled primarily as text rather than as graphics or other media.
-
E.
verseTextArabic
Indicates the Arabic-language text content associated with a specific verse in a scriptural or poetic work.
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eefadf6e608190b42b26ea22c76ec6 |
completed | April 27, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69e632109d048190b4ac3f14fe48d1a0 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:32 p.m.