Triple

T17738453
Position Surface form Disambiguated ID Type / Status
Subject Zaghouan Governorate E442786 entity
Predicate hasCity P316 FINISHED
Object Saouaf
Saouaf is a town located in the Zaghouan Governorate of northeastern Tunisia.
E1284932 NE FINISHED

How this triple was built (4 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: Saouaf | Statement: [Zaghouan Governorate, hasCity, Saouaf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saouaf
Context triple: [Zaghouan Governorate, hasCity, Saouaf]
  • A. Youssoufia
    Youssoufia is a Moroccan city known for its phosphate mining industry and its location within the Marrakesh-Safi region.
  • B. Kalfou
    Kalfou is a powerful and feared Haitian Vodou spirit associated with the crossroads, chaos, and the control of spiritual pathways.
  • C. Bechloul
    Bechloul is a town and commune located in northern Algeria within the Bouira Province.
  • D. Sahnun
    Sahnun was a prominent 9th-century Islamic jurist from North Africa whose compilation of legal opinions, the Mudawwana, became a foundational text of the Maliki school of Sunni jurisprudence.
  • E. Lakhdar
    Lakhdar is an Arabic masculine given name most notably borne by Algerian diplomat Lakhdar Brahimi.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Saouaf
Triple: [Zaghouan Governorate, hasCity, Saouaf]
Generated description
Saouaf is a town located in the Zaghouan Governorate of northeastern Tunisia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saouaf
Target entity description: Saouaf is a town located in the Zaghouan Governorate of northeastern Tunisia.
  • A. Youssoufia
    Youssoufia is a Moroccan city known for its phosphate mining industry and its location within the Marrakesh-Safi region.
  • B. Kalfou
    Kalfou is a powerful and feared Haitian Vodou spirit associated with the crossroads, chaos, and the control of spiritual pathways.
  • C. Bechloul
    Bechloul is a town and commune located in northern Algeria within the Bouira Province.
  • D. Sahnun
    Sahnun was a prominent 9th-century Islamic jurist from North Africa whose compilation of legal opinions, the Mudawwana, became a foundational text of the Maliki school of Sunni jurisprudence.
  • E. Lakhdar
    Lakhdar is an Arabic masculine given name most notably borne by Algerian diplomat Lakhdar Brahimi.
  • F. None of above. chosen

Provenance (5 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47aca27448190943c75e723ceefcc completed April 19, 2026, 6:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0242fb5e7c819096b611fe936f4ce0 completed May 11, 2026, 8:58 p.m.
NEDg Description generation batch_6a0244f53f2c81909ee3dc16ff3e512e completed May 11, 2026, 9:07 p.m.
NED2 Entity disambiguation (via description) batch_6a02459d9ab48190b8b28b75f412c64e completed May 11, 2026, 9:09 p.m.
Created at: April 10, 2026, 10:09 a.m.