Triple

T10130028
Position Surface form Disambiguated ID Type / Status
Subject Markkleeberg E226311 entity
Predicate adjacentTo P224 FINISHED
Object Belgershain
Belgershain is a small municipality in the Leipzig district of Saxony, Germany, situated southeast of the city of Leipzig.
 E842727 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: Belgershain | Statement: [Markkleeberg, adjacentTo, Belgershain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Belgershain
Context triple: [Markkleeberg, adjacentTo, Belgershain]
  • A. Breyten
    Breyten is the given name of Breyten Breytenbach, the renowned South African poet, painter, and anti-apartheid activist.
  • B. Bechtsrieth
    Bechtsrieth is a small municipality in the Upper Palatinate region of Bavaria, Germany.
  • C. Stutterheim
    Stutterheim is a small town in South Africa’s Eastern Cape province, known for its forestry, agriculture, and scenic setting near the Amathole Mountains.
  • D. Boechout
    Boechout is a municipality in the Belgian province of Antwerp, known for its suburban character and proximity to the city of Antwerp.
  • E. Blatzheim
    Blatzheim is a village and district within the town of Kerpen in North Rhine-Westphalia, Germany.
  • 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: Belgershain
Triple: [Markkleeberg, adjacentTo, Belgershain]
Generated description
Belgershain is a small municipality in the Leipzig district of Saxony, Germany, situated southeast of the city of Leipzig.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Belgershain
Target entity description: Belgershain is a small municipality in the Leipzig district of Saxony, Germany, situated southeast of the city of Leipzig.
  • A. Breyten
    Breyten is the given name of Breyten Breytenbach, the renowned South African poet, painter, and anti-apartheid activist.
  • B. Bechtsrieth
    Bechtsrieth is a small municipality in the Upper Palatinate region of Bavaria, Germany.
  • C. Stutterheim
    Stutterheim is a small town in South Africa’s Eastern Cape province, known for its forestry, agriculture, and scenic setting near the Amathole Mountains.
  • D. Boechout
    Boechout is a municipality in the Belgian province of Antwerp, known for its suburban character and proximity to the city of Antwerp.
  • E. Blatzheim
    Blatzheim is a village and district within the town of Kerpen in North Rhine-Westphalia, Germany.
  • 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd33438988190be45878f98695816 completed April 2, 2026, 2:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc7c50b08190a04aa2f58a6c300a completed April 5, 2026, 8:56 p.m.
NEDg Description generation batch_69d2cecd67448190a28a90148ad83c20 completed April 5, 2026, 9:06 p.m.
NED2 Entity disambiguation (via description) batch_69d2cf4d259881909f44bf1ec39524de completed April 5, 2026, 9:08 p.m.
Created at: March 30, 2026, 9:05 p.m.