Triple

T21894339
Position Surface form Disambiguated ID Type / Status
Subject Ziyad ibn Abih E540635 entity
Predicate controlled P4700 FINISHED
Object Sijistan 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: Sijistan | Statement: [Ziyad ibn Abih, controlled, Sijistan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sijistan
Context triple: [Ziyad ibn Abih, controlled, Sijistan]
  • A. Sijistan chosen
    Sijistan (also known as Sistan) is a historical region in eastern Iran and southwestern Afghanistan that was an important center of early Islamic scholarship and culture.
  • B. Elbistan
    Elbistan is a large town and district in southern Turkey known for its agricultural production and significant lignite-fueled thermal power plants.
  • C. Zriba
    Zriba is a small town in northeastern Tunisia, known for its traditional architecture and proximity to the historic city of Zaghouan.
  • D. Zangilan
    Zangilan is a town in southwestern Azerbaijan that serves as an administrative and transport hub near the borders with Armenia and Iran.
  • E. Ouadhia
    Ouadhia is a town and commune located in northern Algeria within the Kabylie region.
  • 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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc539708190a42f202e7404a213 completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:07 p.m.