Triple

T12256927
Position Surface form Disambiguated ID Type / Status
Subject Fulani Empire E292125 entity
Predicate hasCenter P35 FINISHED
Object Sokoto E66570 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: Sokoto | Statement: [Fulani Empire, hasCenter, Sokoto]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sokoto
Context triple: [Fulani Empire, hasCenter, Sokoto]
  • A. Sokoto chosen
    Sokoto is a historic city in northwestern Nigeria that served as the capital of the Sokoto Caliphate and remains an important cultural and Islamic scholarly center.
  • B. Kano
    Kano is a major commercial and industrial city in northern Nigeria and one of the country’s oldest urban centers.
  • C. Kano
    Kano is a long-running Mortal Kombat villain known as a ruthless mercenary and leader of the Black Dragon crime syndicate, often depicted with a cybernetic eye and expertise in knives and dirty fighting tactics.
  • D. Dutse
    Dutse is a city in northern Nigeria that serves as the administrative and economic center of Jigawa State.
  • E. Dutse
    Dutse is a locality within Nigeria’s Federal Capital Territory, situated in the Bwari Area Council on the outskirts of Abuja.
  • 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_69d6ab67950c8190be08450a06228c4b completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91ccadc3c81908fe68adc3fdcc851 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8b9717c8190b8ac71989d3b3582 completed May 3, 2026, 2:53 a.m.
Created at: April 8, 2026, 9:52 p.m.