Triple

T4638540
Position Surface form Disambiguated ID Type / Status
Subject Unna E101592 entity
Predicate hasTwinTown P919 FINISHED
Object Ajka
Ajka is a town in western Hungary known for its industrial heritage, particularly in mining and alumina production.
 E456759 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: Ajka | Statement: [Unna, hasTwinTown, Ajka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ajka
Context triple: [Unna, hasTwinTown, Ajka]
  • A. Paju
    Paju is a city in South Korea near the Demilitarized Zone, known for its historical sites, cultural complexes, and role as a border hub with North Korea.
  • B. Kirovakan
    Kirovakan is the former name of Vanadzor, a major industrial city in northern Armenia.
  • C. Kars
    Kars is a historic city in northeastern Turkey known for its medieval fortifications, strategic location near the Caucasus, and role as a former regional capital in various Armenian and Ottoman periods.
  • D. Gudermes
    Gudermes is a town in the Chechen Republic of Russia that serves as an important regional transport and administrative center.
  • E. Amursk
    Amursk is a small industrial town in Russia’s Far East, situated on the Amur River and known for its timber and pulp-and-paper industries.
  • 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: Ajka
Triple: [Unna, hasTwinTown, Ajka]
Generated description
Ajka is a town in western Hungary known for its industrial heritage, particularly in mining and alumina production.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ajka
Target entity description: Ajka is a town in western Hungary known for its industrial heritage, particularly in mining and alumina production.
  • A. Paju
    Paju is a city in South Korea near the Demilitarized Zone, known for its historical sites, cultural complexes, and role as a border hub with North Korea.
  • B. Kirovakan
    Kirovakan is the former name of Vanadzor, a major industrial city in northern Armenia.
  • C. Kars
    Kars is a historic city in northeastern Turkey known for its medieval fortifications, strategic location near the Caucasus, and role as a former regional capital in various Armenian and Ottoman periods.
  • D. Gudermes
    Gudermes is a town in the Chechen Republic of Russia that serves as an important regional transport and administrative center.
  • E. Amursk
    Amursk is a small industrial town in Russia’s Far East, situated on the Amur River and known for its timber and pulp-and-paper industries.
  • 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_69bd43d3bc7c81908f81fcf380476b0f completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a64214481908a207e8070cc7a45 completed March 20, 2026, 2:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfacf3cb08190a080e5ed1063902f completed March 21, 2026, 1:56 a.m.
NEDg Description generation batch_69bdfb70b9d48190a32c5cc753c45aab completed March 21, 2026, 1:59 a.m.
NED2 Entity disambiguation (via description) batch_69bdfc54e194819080b1eb5b9f0dfe9e completed March 21, 2026, 2:03 a.m.
Created at: March 20, 2026, 1:13 p.m.