Triple

T7468802
Position Surface form Disambiguated ID Type / Status
Subject Shabaka E176450 entity
Predicate ruledOver P1715 FINISHED
Object Kush E636861 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: Kush | Statement: [Shabaka, ruledOver, Kush]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kush
Context triple: [Shabaka, ruledOver, Kush]
  • A. Makuria
    Makuria was a medieval Nubian kingdom in what is now Sudan, notable for its Christian culture and long resistance to Arab expansion.
  • B. Nuba
    Nuba is a Palestinian village located in the Hebron Governorate in the southern West Bank.
  • C. Napatan Kush chosen
    Napatan Kush was an ancient Nubian kingdom centered at Napata that flourished along the Nile in what is now Sudan, known for its powerful rulers, pyramids, and close cultural ties with ancient Egypt.
  • D. Nubia
    Nubia is a historic region along the Nile in southern Egypt and northern Sudan, renowned for its ancient civilizations, archaeological sites, and monumental temples.
  • E. Meroë
    Meroë was an ancient city of the Kingdom of Kush in present-day Sudan, renowned as a royal capital and major center of Nubian culture, iron production, and distinctive pyramid burials.
  • 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_69c69f223fd88190b4c69b95d7cbeeda completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f3f6f23881908e3e80b0c7335a15 completed March 27, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83475392c8190a51d24e1530c0c83 completed March 28, 2026, 8:05 p.m.
Created at: March 27, 2026, 3:40 p.m.