Triple
T1990063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thaana script |
E43230
|
entity |
| Predicate | hasDiacriticOrigin |
P18659
|
FINISHED |
| Object | influenced by Arabic harakat |
E169408
|
NE FINISHED |
How this triple was built (3 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: influenced by Arabic harakat | Statement: [Thaana script, hasDiacriticOrigin, influenced by Arabic harakat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: influenced by Arabic harakat Context triple: [Thaana script, hasDiacriticOrigin, influenced by Arabic harakat]
-
A.
Tajwid
Tajwid is the set of rules and techniques governing the precise and melodious pronunciation of Arabic letters and words during the recitation of the Quran.
-
B.
Arabic-script typography
chosen
Arabic-script typography is the design and arrangement of text using the Arabic writing system, encompassing its calligraphic styles, contextual letter forms, and specialized typographic conventions across print and digital media.
-
C.
Perso-Arabic script
The Perso-Arabic script is a modified form of the Arabic writing system, expanded with additional letters and conventions to represent the sounds of Persian and several other languages across the Middle East and South Asia.
-
D.
Arabic Supplement
Arabic Supplement is a Unicode block that contains additional Arabic script characters used for extended orthographic and contextual purposes beyond the basic Arabic block.
-
E.
Arabic alphabet
The Arabic alphabet is a cursive, right-to-left abjad script used across the Arab world and adapted for many other languages, including Persian, Urdu, and Pashto.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDiacriticOrigin Context triple: [Thaana script, hasDiacriticOrigin, influenced by Arabic harakat]
-
A.
usesDiacritics
Indicates that the referenced text or linguistic element employs diacritical marks as part of its written form.
-
B.
diacriticType
chosen
Indicates the specific kind or category of diacritic mark associated with a character or symbol.
-
C.
hasAccent
Indicates that an entity speaks with or possesses a particular accent or distinctive pronunciation style.
-
D.
hasCyrillicAlphabetForm
Indicates that an entity has a corresponding representation or form written in the Cyrillic alphabet.
-
E.
hasNameOrigin
Indicates that the origin or source of an entity’s name is specified by the related entity.
- F. None of above.
Provenance (4 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_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0336177c8190bb9d3d921fff13e8 |
completed | March 8, 2026, 11:16 p.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:37 p.m.