Triple

T22686728
Position Surface form Disambiguated ID Type / Status
Subject سوسة E560936 entity
Predicate hasFortification P8412 FINISHED
Object أسوار سوسة
أسوار سوسة هي التحصينات التاريخية التي تطوّق المدينة العتيقة في سوسة التونسية وتُعد من أبرز معالمها الأثرية والدفاعية.
 E1549636 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: أسوار سوسة | Statement: [سوسة, hasFortification, أسوار سوسة]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: أسوار سوسة
Context triple: [سوسة, hasFortification, أسوار سوسة]
  • A. Sarrin
    Sarrin is a town in northern Syria located in the Ayn al-Arab (Kobanî) region, known for its strategic position near the Euphrates River and the Turkish border.
  • B. Sarz
    Sarz is a Nigerian record producer and songwriter renowned for crafting hit Afrobeats tracks for major artists across Africa.
  • C. Sabor
    Sabor is a river in northeastern Portugal that flows through the Trás-os-Montes region before joining the Douro River.
  • D. Sabor
    Sabor is the unicameral national legislature and representative body of the Republic of Croatia.
  • E. Mehunaise
    Mehunaise is the French demonym for a female inhabitant of the town of Mehun-sur-Yèvre in central France.
  • 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: أسوار سوسة
Triple: [سوسة, hasFortification, أسوار سوسة]
Generated description
أسوار سوسة هي التحصينات التاريخية التي تطوّق المدينة العتيقة في سوسة التونسية وتُعد من أبرز معالمها الأثرية والدفاعية.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: أسوار سوسة
Target entity description: أسوار سوسة هي التحصينات التاريخية التي تطوّق المدينة العتيقة في سوسة التونسية وتُعد من أبرز معالمها الأثرية والدفاعية.
  • A. Sarrin
    Sarrin is a town in northern Syria located in the Ayn al-Arab (Kobanî) region, known for its strategic position near the Euphrates River and the Turkish border.
  • B. Sarz
    Sarz is a Nigerian record producer and songwriter renowned for crafting hit Afrobeats tracks for major artists across Africa.
  • C. Sabor
    Sabor is the unicameral national legislature and representative body of the Republic of Croatia.
  • D. Sabor
    Sabor is a river in northeastern Portugal that flows through the Trás-os-Montes region before joining the Douro River.
  • E. Mehunaise
    Mehunaise is the French demonym for a female inhabitant of the town of Mehun-sur-Yèvre in central France.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178649aac8190a9d41f5d82895bdf completed April 29, 2026, 3:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b73f6da688190a7c5c432bb0f6feb completed May 18, 2026, 8:17 p.m.
NEDg Description generation batch_6a0b79f9ebe48190ba069f68c3900be8 completed May 18, 2026, 8:43 p.m.
NED2 Entity disambiguation (via description) batch_6a0b7a9565f08190acee542633fd7b49 completed May 18, 2026, 8:46 p.m.
Created at: April 17, 2026, 3:13 p.m.