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.