Triple

T13367263
Position Surface form Disambiguated ID Type / Status
Subject Forest, Belgium E318970 entity
Predicate hasTwinTown P919 FINISHED
Object Sahab, Jordan
Sahab is an industrial town in Jordan, located southeast of Amman, known for its factories and growing residential areas.
 E1037685 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: Sahab, Jordan | Statement: [Forest, Belgium, hasTwinTown, Sahab, Jordan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sahab, Jordan
Context triple: [Forest, Belgium, hasTwinTown, Sahab, Jordan]
  • A. Dhiban, Jordan
    Dhiban, Jordan is an archaeological town in central Jordan best known as the ancient Moabite city of Dibon, where the famous Mesha Stele was discovered.
  • B. ערבה
    ערבה היא בקעה מדברית רחבת ידיים בדרום ארץ ישראל וירדן, המשתרעת בין ים המלח למפרץ אילת.
  • C. Mafraq
    Mafraq is a city in northern Jordan that serves as a strategic transport hub and gateway to the Syrian border and surrounding desert regions.
  • D. As-Suwayda
    As-Suwayda is a city in southwestern Syria known as a center of the Druze community and for its nearby ancient and volcanic landscapes.
  • E. Umm al-Ghanam
    Umm al-Ghanam is a village in northern Israel that forms part of the Arab local council of Shibli–Umm al-Ghanam near Mount Tabor.
  • 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: Sahab, Jordan
Triple: [Forest, Belgium, hasTwinTown, Sahab, Jordan]
Generated description
Sahab is an industrial town in Jordan, located southeast of Amman, known for its factories and growing residential areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sahab, Jordan
Target entity description: Sahab is an industrial town in Jordan, located southeast of Amman, known for its factories and growing residential areas.
  • A. Dhiban, Jordan
    Dhiban, Jordan is an archaeological town in central Jordan best known as the ancient Moabite city of Dibon, where the famous Mesha Stele was discovered.
  • B. ערבה
    ערבה היא בקעה מדברית רחבת ידיים בדרום ארץ ישראל וירדן, המשתרעת בין ים המלח למפרץ אילת.
  • C. Mafraq
    Mafraq is a city in northern Jordan that serves as a strategic transport hub and gateway to the Syrian border and surrounding desert regions.
  • D. As-Suwayda
    As-Suwayda is a city in southwestern Syria known as a center of the Druze community and for its nearby ancient and volcanic landscapes.
  • E. Umm al-Ghanam
    Umm al-Ghanam is a village in northern Israel that forms part of the Arab local council of Shibli–Umm al-Ghanam near Mount Tabor.
  • 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_69d806b7bbac8190b85278c87fa7aff3 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dadcd652d48190a782fd1f57f34b6a completed April 11, 2026, 11:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f72680df088190b8dbcc8ad0d7366e completed May 3, 2026, 10:42 a.m.
NEDg Description generation batch_69f727512c94819091985c7942f40b31 completed May 3, 2026, 10:45 a.m.
NED2 Entity disambiguation (via description) batch_69f72b77d650819092c02f6488b2cfb2 completed May 3, 2026, 11:03 a.m.
Created at: April 9, 2026, 9:32 p.m.