Triple

T9639787
Position Surface form Disambiguated ID Type / Status
Subject Uusikaupunki E233031 entity
Predicate hasTwinTown P919 FINISHED
Object Kunda
Kunda is a small industrial town in northern Estonia known for its cement industry and archaeological significance.
 E813200 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: Kunda | Statement: [Uusikaupunki, hasTwinTown, Kunda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kunda
Context triple: [Uusikaupunki, hasTwinTown, Kunda]
  • A. Kaonde
    Kaonde is a Bantu language spoken primarily by the Kaonde people of northwestern Zambia and parts of the Democratic Republic of the Congo.
  • B. Lunda
    Lunda is a Bantu language spoken primarily by the Lunda people in parts of Zambia, Angola, and the Democratic Republic of the Congo.
  • C. Kindu
    Kindu is a city in the eastern Democratic Republic of the Congo that serves as the capital of Maniema Province and an important regional transport hub.
  • D. Kibondo
    Kibondo is a town in western Tanzania that serves as an administrative and commercial center in the Kigoma Region.
  • E. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • 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: Kunda
Triple: [Uusikaupunki, hasTwinTown, Kunda]
Generated description
Kunda is a small industrial town in northern Estonia known for its cement industry and archaeological significance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kunda
Target entity description: Kunda is a small industrial town in northern Estonia known for its cement industry and archaeological significance.
  • A. Kaonde
    Kaonde is a Bantu language spoken primarily by the Kaonde people of northwestern Zambia and parts of the Democratic Republic of the Congo.
  • B. Lunda
    Lunda is a Bantu language spoken primarily by the Lunda people in parts of Zambia, Angola, and the Democratic Republic of the Congo.
  • C. Kindu
    Kindu is a city in the eastern Democratic Republic of the Congo that serves as the capital of Maniema Province and an important regional transport hub.
  • D. Kibondo
    Kibondo is a town in western Tanzania that serves as an administrative and commercial center in the Kigoma Region.
  • E. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • 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_69ca848a5a908190aad251f4137b0c3a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b532aa4819087b56be6f5635126 completed April 1, 2026, 10:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69d189fd53fc8190bc36f2b8e0e21036 completed April 4, 2026, 10 p.m.
NEDg Description generation batch_69d18acf86588190bc000f701bcaaa1c completed April 4, 2026, 10:03 p.m.
NED2 Entity disambiguation (via description) batch_69d18ba396cc8190a3ded2ac3968c553 completed April 4, 2026, 10:07 p.m.
Created at: March 30, 2026, 8:12 p.m.