Triple

T22686699
Position Surface form Disambiguated ID Type / Status
Subject سوسة E560936 entity
Predicate country P26 FINISHED
Object تونس 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: تونس | Statement: [سوسة, country, تونس]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: تونس
Context triple: [سوسة, country, تونس]
  • A. تونس chosen
    تونس هي دولة عربية تقع في شمال أفريقيا على ساحل البحر الأبيض المتوسط وعاصمتها مدينة تونس.
  • B. Tunis
    Tunis is the capital and largest city of Tunisia, serving as a major political, economic, and cultural center in the Arab world.
  • C. Sfax
    Sfax is a major port city on Tunisia’s eastern coast, known as an economic hub and a significant center of political activism during the Tunisian Revolution.
  • D. Tunis Governorate
    Tunis Governorate is an administrative region in northeastern Tunisia that encompasses the nation’s capital city, Tunis, and serves as its political and economic center.
  • E. Mahdia
    Mahdia is a historic coastal city in present-day Tunisia that served as the first capital of the Fatimid Caliphate and an important Mediterranean trading and naval center.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178649aac8190a9d41f5d82895bdf completed April 29, 2026, 3:17 a.m.
Created at: April 17, 2026, 3:13 p.m.