Triple

T2915615
Position Surface form Disambiguated ID Type / Status
Subject Vogtland E78598 entity
Predicate contains P35 FINISHED
Object Greiz
Greiz is a historic town in eastern Thuringia, Germany, known for its castles and role as a former residence of the Princes of Reuss.
 E310957 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: Greiz | Statement: [Vogtland, contains, Greiz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Greiz
Context triple: [Vogtland, contains, Greiz]
  • A. Altenburg
    Altenburg is a historic town in eastern Thuringia, Germany, known for its playing-card tradition and as the birthplace of the card game Skat.
  • B. Coburg
    Coburg is a historic town in northern Bavaria, Germany, known for its well-preserved medieval architecture and its former role as the seat of the Duchy of Saxe-Coburg and Gotha.
  • C. Wittenau
    Wittenau is a locality in the Reinickendorf borough of Berlin, Germany, known primarily as a residential area with good transport connections.
  • D. Bamberg
    Bamberg is a historic city in northern Bavaria, Germany, renowned for its well-preserved medieval old town and status as a UNESCO World Heritage Site.
  • E. Lankwitz
    Lankwitz is a residential locality in the southwestern part of Berlin, known for its quiet neighborhoods, green spaces, and mix of historic and modern 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: Greiz
Triple: [Vogtland, contains, Greiz]
Generated description
Greiz is a historic town in eastern Thuringia, Germany, known for its castles and role as a former residence of the Princes of Reuss.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Greiz
Target entity description: Greiz is a historic town in eastern Thuringia, Germany, known for its castles and role as a former residence of the Princes of Reuss.
  • A. Altenburg
    Altenburg is a historic town in eastern Thuringia, Germany, known for its playing-card tradition and as the birthplace of the card game Skat.
  • B. Coburg
    Coburg is a historic town in northern Bavaria, Germany, known for its well-preserved medieval architecture and its former role as the seat of the Duchy of Saxe-Coburg and Gotha.
  • C. Wittenau
    Wittenau is a locality in the Reinickendorf borough of Berlin, Germany, known primarily as a residential area with good transport connections.
  • D. Bamberg
    Bamberg is a historic city in northern Bavaria, Germany, renowned for its well-preserved medieval old town and status as a UNESCO World Heritage Site.
  • E. Lankwitz
    Lankwitz is a residential locality in the southwestern part of Berlin, known for its quiet neighborhoods, green spaces, and mix of historic and modern 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad96a1a9f8819095fe3198e9d3f6b0 completed March 8, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b056249b5c8190b388088bf047616f completed March 10, 2026, 5:34 p.m.
NEDg Description generation batch_69b06434bef48190848d8ab1aa59937c completed March 10, 2026, 6:34 p.m.
NED2 Entity disambiguation (via description) batch_69b064a3b41481909214a09eae0b092b completed March 10, 2026, 6:36 p.m.
Created at: March 8, 2026, 2:52 p.m.