Triple
T2721622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan al-Atrash |
E60092
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | al-Atrash |
E213463
|
NE 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: al-Atrash | Statement: [Sultan al-Atrash, familyName, al-Atrash]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: al-Atrash Context triple: [Sultan al-Atrash, familyName, al-Atrash]
-
A.
Sahnun
Sahnun was a prominent 9th-century Islamic jurist from North Africa whose compilation of legal opinions, the Mudawwana, became a foundational text of the Maliki school of Sunni jurisprudence.
-
B.
Butrus
Butrus is an alternative transliteration of the Arabic given name "Boutros," itself derived from "Peter."
-
C.
al-Bahuti
Al-Bahuti was a prominent 16th–17th century Hanbali jurist and legal theorist whose works became standard references in later Hanbali jurisprudence.
-
D.
Tolba Marzuq
Tolba Marzuq is a character in Naguib Mahfouz’s novel "Miramar," representing one of the diverse boarders at the Alexandria pension whose interactions reflect Egypt’s social and political tensions in the 1960s.
-
E.
al-Natsheh
chosen
al-Natsheh is an Arabic family name associated with Palestinian individuals and families, including political and public figures.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ab4b746d248190958e052045c09255 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdab1cb808190b0789c76bc9cb090 |
completed | March 7, 2026, 7:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afbbc05d148190b6a0faf10443519d |
completed | March 10, 2026, 6:35 a.m. |
Created at: March 6, 2026, 9:55 p.m.