Triple

T3581123
Position Surface form Disambiguated ID Type / Status
Subject Plauen E75799 entity
Predicate twinTown P1072 FINISHED
Object Aš
Aš is a town in the Karlovy Vary Region of the Czech Republic, located near the German border and known for its textile industry and borderland history.
 E370428 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: Aš | Statement: [Plauen, twinTown, Aš]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Aš
Context triple: [Plauen, twinTown, Aš]
  • A. Ako
    Ako is a coastal city in southwestern Hyogo Prefecture, Japan, historically known for its salt production and the story of the Forty-seven Ronin.
  • B. Atsi
    Atsi is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • C. Simas
    Simas is a surname most notably associated with David Simas, an American lawyer and former political advisor who served in the Obama administration.
  • D. Una
    Una is a feminine given name of Latin origin meaning "one" or "unity," used in various cultures and literary works.
  • E. Una
    Una is a river in the Western Balkans, known for its clear turquoise waters and scenic canyons along the border of Bosnia and Herzegovina and Croatia.
  • 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: Aš
Triple: [Plauen, twinTown, Aš]
Generated description
Aš is a town in the Karlovy Vary Region of the Czech Republic, located near the German border and known for its textile industry and borderland history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Aš
Target entity description: Aš is a town in the Karlovy Vary Region of the Czech Republic, located near the German border and known for its textile industry and borderland history.
  • A. Ako
    Ako is a coastal city in southwestern Hyogo Prefecture, Japan, historically known for its salt production and the story of the Forty-seven Ronin.
  • B. Atsi
    Atsi is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • C. Simas
    Simas is a surname most notably associated with David Simas, an American lawyer and former political advisor who served in the Obama administration.
  • D. Una
    Una is a feminine given name of Latin origin meaning "one" or "unity," used in various cultures and literary works.
  • E. Una
    Una is a river in the Western Balkans, known for its clear turquoise waters and scenic canyons along the border of Bosnia and Herzegovina and Croatia.
  • 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_69ad85d6dc3c8190b491b79b83e25461 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc101738c81908d38987f8fa291ef completed March 8, 2026, 6:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bbc95fa881909846a6d53ba6a24e completed March 13, 2026, 7:24 a.m.
NEDg Description generation batch_69b3bcae84a48190b085f253773cd14f completed March 13, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_69b3f90df47c81908855021f68ca7ec8 completed March 13, 2026, 11:46 a.m.
Created at: March 8, 2026, 3:21 p.m.