Triple

T16982537
Position Surface form Disambiguated ID Type / Status
Subject Ahmad Shah Durrani E411980 entity
Predicate dynasty P1547 FINISHED
Object Sadozai NE NERFINISHED

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: Sadozai | Statement: [Ahmad Shah Durrani, dynasty, Sadozai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sadozai
Context triple: [Ahmad Shah Durrani, dynasty, Sadozai]
  • A. Sadozai chosen
    Sadozai is a Pashtun royal dynasty and clan historically associated with the founding rulers of the Durrani Empire in Afghanistan.
  • B. Ōtomo
    Ōtomo is a historical Japanese clan name borne by several notable aristocrats and poets in ancient Japan.
  • C. Hiranuma
    Hiranuma is a notable district within Nishi Ward in Yokohama, Japan, known as part of the city’s central urban area.
  • D. Michitsura
    Michitsura is a Japanese given name, notably borne by the Imperial Japanese Army general Nozu Michitsura.
  • E. Masaharu
    Masaharu is a Japanese masculine given name that can be written with various kanji combinations and is borne by several notable figures in Japanese history and culture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d886ca8f348190812768ea8d5055ce completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d18830ac8190a20c89a87379ae94 completed April 18, 2026, 6:46 p.m.
Created at: April 10, 2026, 5:32 a.m.