Triple

T2186571
Position Surface form Disambiguated ID Type / Status
Subject As-Saffah E49164 entity
Predicate predecessor P97 FINISHED
Object Marwan II E44081 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: Marwan II | Statement: [As-Saffah, predecessor, Marwan II]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marwan II
Context triple: [As-Saffah, predecessor, Marwan II]
  • A. Marwan II chosen
    Marwan II was the final Umayyad caliph, whose defeat marked the end of Umayyad rule in the Middle East and the rise of the Abbasid Caliphate.
  • B. Marwan I
    Marwan I was an Umayyad caliph who played a pivotal role in ending the Second Fitna and consolidating Umayyad rule over the early Islamic empire.
  • C. Sultan al-Atrash
    Sultan al-Atrash was a prominent 20th-century Druze leader and Syrian nationalist revolutionary best known for leading the Great Syrian Revolt against French colonial rule in the 1920s.
  • D. Said Mahran
    Said Mahran is the vengeful, psychologically tormented ex-convict protagonist of Naguib Mahfouz’s novel "The Thief and the Dogs."
  • E. Amr ibn Ma‘di Yakrib
    Amr ibn Ma‘di Yakrib was a famed pre-Islamic Arab warrior and poet of the Zubayd tribe, celebrated in Arabic tradition for his exceptional bravery and skill in battle.
  • 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_69a88aa72d348190a9544bb5b8a4e71d completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbf1152688190955c14c0937deefd completed March 7, 2026, 6 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7efa34e88190a6907515b574f752 completed March 9, 2026, 8:04 a.m.
Created at: March 4, 2026, 7:45 p.m.