Triple

T8256015
Position Surface form Disambiguated ID Type / Status
Subject Lake Van E193071 entity
Predicate locatedNear P294 FINISHED
Object city of Van
The city of Van is a historic urban center in eastern Turkey, known as the cultural and economic hub of the region and famed for its ancient heritage and proximity to Lake Van.
 E721125 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: city of Van | Statement: [Lake Van, locatedNear, city of Van]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: city of Van
Context triple: [Lake Van, locatedNear, city of Van]
  • A. Vanne
    Vanne is a river in north-central France that serves as a tributary of the Yonne.
  • B. Zaqatala city
    Zaqatala city is an administrative and economic center in northwestern Azerbaijan, known for its multicultural population and proximity to the Caucasus Mountains.
  • C. Orbost
    Orbost is a small rural town in East Gippsland, Victoria, Australia, known as a service centre for the surrounding farming and forestry region near the Snowy River.
  • D. Batu City
    Batu City is a highland tourist city in East Java, Indonesia, known for its cool climate, mountain scenery, and numerous recreational attractions.
  • E. Varos
    Varos is a village on the Greek island of Lemnos in the northern Aegean Sea.
  • 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: city of Van
Triple: [Lake Van, locatedNear, city of Van]
Generated description
The city of Van is a historic urban center in eastern Turkey, known as the cultural and economic hub of the region and famed for its ancient heritage and proximity to Lake Van.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: city of Van
Target entity description: The city of Van is a historic urban center in eastern Turkey, known as the cultural and economic hub of the region and famed for its ancient heritage and proximity to Lake Van.
  • A. Vanne
    Vanne is a river in north-central France that serves as a tributary of the Yonne.
  • B. Zaqatala city
    Zaqatala city is an administrative and economic center in northwestern Azerbaijan, known for its multicultural population and proximity to the Caucasus Mountains.
  • C. Orbost
    Orbost is a small rural town in East Gippsland, Victoria, Australia, known as a service centre for the surrounding farming and forestry region near the Snowy River.
  • D. Batu City
    Batu City is a highland tourist city in East Java, Indonesia, known for its cool climate, mountain scenery, and numerous recreational attractions.
  • E. Varos
    Varos is a village on the Greek island of Lemnos in the northern Aegean Sea.
  • 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_69ca82dfad9c8190b8cd18fb89f50f40 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb78f9f680819088f1d56e0f98974f completed March 31, 2026, 7:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd3553b48881909cc72e443aad9539 completed April 1, 2026, 3:10 p.m.
NEDg Description generation batch_69cd37a71af481909e82aa29ae558c4a completed April 1, 2026, 3:20 p.m.
NED2 Entity disambiguation (via description) batch_69cd4f0055dc8190803a7c412533aec4 completed April 1, 2026, 4:59 p.m.
Created at: March 30, 2026, 5:49 p.m.