Triple

T14490594
Position Surface form Disambiguated ID Type / Status
Subject Ahmad Shah Durrani E359350 entity
Predicate placeOfDeath P21 FINISHED
Object Maruf E359350 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: Maruf | Statement: [Ahmad Shah Durrani, placeOfDeath, Maruf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maruf
Context triple: [Ahmad Shah Durrani, placeOfDeath, Maruf]
  • A. Maruf chosen
    Maruf is a town in present-day Afghanistan historically notable as the place where Ahmad Shah Durrani, founder of the Durrani Empire, died.
  • B. Abdus
    Abdus is a given name most notably borne by Abdus Salam, the Pakistani theoretical physicist and Nobel laureate.
  • C. Fazl
    Fazl is the given name of Fazl-e-Haq Khairabadi, a 19th-century Indian Islamic scholar, philosopher, and prominent figure in the Indian Rebellion of 1857.
  • D. Habib
    Habib is a masculine given name of Arabic origin commonly used in North Africa and the Middle East.
  • E. Rashid
    Rashid, also known as Rosetta, is a historic port city in northern Egypt famed for the discovery of the Rosetta Stone.
  • 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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de930d820481908b9813014dd02540 completed April 14, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d9334708190baa2f8094df3c09e completed May 8, 2026, 4:58 a.m.
Created at: April 10, 2026, 1:20 a.m.