Triple

T4206023
Position Surface form Disambiguated ID Type / Status
Subject Susa E86185 entity
Predicate locatedNear P294 FINISHED
Object Dez River
Dez River is a significant river in southwestern Iran that flows through the Khuzestan region and historically supported ancient cities such as Susa.
 E680528 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: Dez River | Statement: [Susa, locatedNear, Dez River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dez River
Context triple: [Susa, locatedNear, Dez River]
  • A. Seim River
    The Seim River is a major tributary of the Desna River in Eastern Europe, flowing through parts of Russia and northern Ukraine.
  • B. Yeso River
    The Yeso River is a significant Andean watercourse in central Chile that feeds into the Maipo River and helps supply water to the Santiago metropolitan region.
  • C. Lotru River
    The Lotru River is a mountain river in Romania that flows through the Southern Carpathians and is known for its hydroelectric developments and scenic valley.
  • D. Tecka River
    The Tecka River is a Patagonian watercourse in Argentina that feeds into the larger Chubut River system.
  • E. Lovat River
    The Lovat River is a waterway in northwestern Russia that flows through the Novgorod region before emptying into Lake Ilmen.
  • 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: Dez River
Triple: [Susa, locatedNear, Dez River]
Generated description
Dez River is a significant river in southwestern Iran that flows through the Khuzestan region and historically supported ancient cities such as Susa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dez River
Target entity description: Dez River is a significant river in southwestern Iran that flows through the Khuzestan region and historically supported ancient cities such as Susa.
  • A. Seim River
    The Seim River is a major tributary of the Desna River in Eastern Europe, flowing through parts of Russia and northern Ukraine.
  • B. Yeso River
    The Yeso River is a significant Andean watercourse in central Chile that feeds into the Maipo River and helps supply water to the Santiago metropolitan region.
  • C. Lotru River
    The Lotru River is a mountain river in Romania that flows through the Southern Carpathians and is known for its hydroelectric developments and scenic valley.
  • D. Tecka River
    The Tecka River is a Patagonian watercourse in Argentina that feeds into the larger Chubut River system.
  • E. Lovat River
    The Lovat River is a waterway in northwestern Russia that flows through the Novgorod region before emptying into Lake Ilmen.
  • 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_69aed93b89f48190a31f6d57c760e42f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af03844314819092639ed7d6ef2c6e completed March 9, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a1f26d948190b887c4ccc19548cc completed March 29, 2026, 3:52 a.m.
NEDg Description generation batch_69c8a295f4108190ac84575f8fe4b3dc completed March 29, 2026, 3:55 a.m.
NED2 Entity disambiguation (via description) batch_69c8a2fe5e4c8190b522820fcc5ece93 completed March 29, 2026, 3:56 a.m.
Created at: March 9, 2026, 3:49 p.m.