Triple

T15962271
Position Surface form Disambiguated ID Type / Status
Subject Bardo E387090 entity
Predicate partOf P40 FINISHED
Object Greater Tunis E1183630 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: Greater Tunis | Statement: [Bardo, partOf, Greater Tunis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greater Tunis
Context triple: [Bardo, partOf, Greater Tunis]
  • A. Greater Tunis agglomeration chosen
    The Greater Tunis agglomeration is the large metropolitan area centered on Tunisia’s capital, encompassing Tunis and its surrounding suburban and urban communities.
  • B. Medina of Tunis
    The Medina of Tunis is the historic walled old town of Tunisia’s capital, renowned for its maze-like streets, traditional souks, and rich Islamic architectural heritage.
  • C. Manouba
    Manouba is a city in northern Tunisia that serves as an administrative and educational hub on the outskirts of the capital, Tunis.
  • D. Tunis
    Tunis is the capital and largest city of Tunisia, serving as a major political, economic, and cultural center in the Arab world.
  • E. Medina of Sfax
    The Medina of Sfax is the historic walled old town of Sfax, Tunisia, known for its well-preserved traditional urban fabric, markets, and architecture dating back to the early Islamic period.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15700651c819091c1cc4f60894c35 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00758380d08190bfe73d3e052c1f0a completed May 10, 2026, 12:09 p.m.
Created at: April 10, 2026, 4:53 a.m.