Triple

T5368074
Position Surface form Disambiguated ID Type / Status
Subject Jarash Governorate E103176 entity
Predicate hasTown P847 FINISHED
Object Souf
Souf is a town in Jordan known for its location in the hilly, historically rich region of Jerash in the country’s north.
 E516158 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: Souf | Statement: [Jarash Governorate, hasTown, Souf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Souf
Context triple: [Jarash Governorate, hasTown, Souf]
  • A. Ayat-sur-Sioule
    Ayat-sur-Sioule is a small commune in central France’s Puy-de-Dôme department, known as the birthplace of French Revolutionary general Louis Desaix.
  • B. Sousel
    Sousel is a municipality in Portugal’s Alentejo region, known for its rural landscape, agricultural activities, and traditional whitewashed architecture.
  • C. Murzuq
    Murzuq is an oasis town in southwestern Libya that historically served as an important Saharan trade and caravan center in the Fezzan region.
  • D. Mateur
    Mateur is a town in northern Tunisia known as an agricultural and transport hub situated near Lake Ichkeul.
  • E. Souletin
    Souletin is a distinct dialect of the Basque language traditionally spoken in the Soule (Zuberoa) region of the French Basque Country.
  • 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: Souf
Triple: [Jarash Governorate, hasTown, Souf]
Generated description
Souf is a town in Jordan known for its location in the hilly, historically rich region of Jerash in the country’s north.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Souf
Target entity description: Souf is a town in Jordan known for its location in the hilly, historically rich region of Jerash in the country’s north.
  • A. Ayat-sur-Sioule
    Ayat-sur-Sioule is a small commune in central France’s Puy-de-Dôme department, known as the birthplace of French Revolutionary general Louis Desaix.
  • B. Sousel
    Sousel is a municipality in Portugal’s Alentejo region, known for its rural landscape, agricultural activities, and traditional whitewashed architecture.
  • C. Murzuq
    Murzuq is an oasis town in southwestern Libya that historically served as an important Saharan trade and caravan center in the Fezzan region.
  • D. Mateur
    Mateur is a town in northern Tunisia known as an agricultural and transport hub situated near Lake Ichkeul.
  • E. Souletin
    Souletin is a distinct dialect of the Basque language traditionally spoken in the Soule (Zuberoa) region of the French Basque Country.
  • 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_69bd43daa3e4819090b59d127db70e57 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd86856f688190a34ab93619bae134 completed March 20, 2026, 5:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf2928859881908ac238feca132d07 completed March 21, 2026, 11:26 p.m.
NEDg Description generation batch_69bf2a09891c81908509695a41d1aa02 completed March 21, 2026, 11:30 p.m.
NED2 Entity disambiguation (via description) batch_69bf2ad48fc48190bb0c7de4df879c3b completed March 21, 2026, 11:33 p.m.
Created at: March 20, 2026, 2:02 p.m.