Triple

T20845649
Position Surface form Disambiguated ID Type / Status
Subject Kairouan Governorate E513217 entity
Predicate hasMajorCity P316 FINISHED
Object Sbikha 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: Sbikha | Statement: [Kairouan Governorate, hasMajorCity, Sbikha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sbikha
Context triple: [Kairouan Governorate, hasMajorCity, Sbikha]
  • A. Sbeitla chosen
    Sbeitla is an ancient Roman archaeological site and modern town in central Tunisia, noted for its well-preserved temples and forum.
  • B. Bakhdida
    Bakhdida is a historically Assyrian Christian town in northern Iraq, known for its ancient churches and location in the Nineveh Plains near Mosul.
  • C. Mahboula
    Mahboula is a coastal residential district in the Ahmadi Governorate of Kuwait, known for its high-rise apartments and proximity to Kuwait City.
  • D. Al Kheesa
    Al Kheesa is a village in the Al Daayen region of Qatar that has rapidly developed from a traditional settlement into a growing suburban area near Doha.
  • E. Shaiba
    Shaiba is a location in southern Iraq notable as the site of the World War I Battle of Shaiba between British and Ottoman forces.
  • 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_69e0b4f4898081908209e58edb8f9c45 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c34ec254819082610264c7af20c8 completed April 21, 2026, 12:22 a.m.
Created at: April 16, 2026, 12:43 p.m.