Triple
T9220702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shahada |
E221351
|
entity |
| Predicate | hasArabicText |
P50395
|
FINISHED |
| Object | أشهد أن لا إله إلا الله وأشهد أن محمدًا رسول الله |
—
|
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: أشهد أن لا إله إلا الله وأشهد أن محمدًا رسول الله | Statement: [Shahada, hasArabicText, أشهد أن لا إله إلا الله وأشهد أن محمدًا رسول الله]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArabicText Context triple: [Shahada, hasArabicText, أشهد أن لا إله إلا الله وأشهد أن محمدًا رسول الله]
-
A.
hasNameInArabic
Indicates that an entity is associated with a specific name expressed in the Arabic language.
-
B.
hasArabicNumeral
Indicates that an entity is associated with, represented by, or expressed using an Arabic numeral.
-
C.
verseTextArabic
chosen
Indicates the Arabic-language text content associated with a specific verse in a scriptural or poetic work.
-
D.
hasGivenNameFormInArabic
Indicates that an entity has a specific given-name form expressed in the Arabic language.
-
E.
hasLadinName
Indicates that an entity is associated with a specific name expressed in the Ladin 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda75b6888190814cfb890e763b8f |
completed | April 1, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69cc7a3daeb481908b0abde3fbc1f1f0 |
completed | April 1, 2026, 1:51 a.m. |
Created at: March 30, 2026, 7:28 p.m.