Triple

T8256018
Position Surface form Disambiguated ID Type / Status
Subject Lake Van E193071 entity
Predicate locatedNear P294 FINISHED
Object Erciş
Erciş is a town and district in Turkey’s Van Province, known for its location on the northern shore of Lake Van and its role as a regional commercial and cultural center.
 E742816 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: Erciş | Statement: [Lake Van, locatedNear, Erciş]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Erciş
Context triple: [Lake Van, locatedNear, Erciş]
  • A. Kalecik
    Kalecik is a district and town in central Turkey known for its historic architecture and the locally famous Kalecik Karası grape variety.
  • B. Muratlı
    Muratlı is a town and district in Turkey’s Thrace region, located within Tekirdağ Province and known for its agricultural and industrial activities.
  • C. Muratpaşa
    Muratpaşa is a central district and municipality of the city of Antalya in southern Turkey, known for its coastal location and urban, touristic character.
  • D. Ereğli
    Ereğli is a district and town in central Turkey known for its agricultural production and location within Konya Province on the Central Anatolian plateau.
  • E. Gümüşhane
    Gümüşhane is a small city in northeastern Turkey known for its mountainous landscape, mining history, and traditional stone architecture.
  • 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: Erciş
Triple: [Lake Van, locatedNear, Erciş]
Generated description
Erciş is a town and district in Turkey’s Van Province, known for its location on the northern shore of Lake Van and its role as a regional commercial and cultural center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Erciş
Target entity description: Erciş is a town and district in Turkey’s Van Province, known for its location on the northern shore of Lake Van and its role as a regional commercial and cultural center.
  • A. Kalecik
    Kalecik is a district and town in central Turkey known for its historic architecture and the locally famous Kalecik Karası grape variety.
  • B. Muratlı
    Muratlı is a town and district in Turkey’s Thrace region, located within Tekirdağ Province and known for its agricultural and industrial activities.
  • C. Muratpaşa
    Muratpaşa is a central district and municipality of the city of Antalya in southern Turkey, known for its coastal location and urban, touristic character.
  • D. Ereğli
    Ereğli is a district and town in central Turkey known for its agricultural production and location within Konya Province on the Central Anatolian plateau.
  • E. Gümüşhane
    Gümüşhane is a small city in northeastern Turkey known for its mountainous landscape, mining history, and traditional stone architecture.
  • 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_69ce8877499081909d8e3762e9c1ed2f completed April 2, 2026, 3:17 p.m.
NEDg Description generation batch_69ce8a442b508190bd8319fda51edc4b completed April 2, 2026, 3:24 p.m.
NED2 Entity disambiguation (via description) batch_69ce8afff50c8190b2dd1a7e0a5a130b completed April 2, 2026, 3:28 p.m.
Created at: March 30, 2026, 5:49 p.m.