Triple

T18246047
Position Surface form Disambiguated ID Type / Status
Subject Kurzeme E436956 entity
Predicate containsTown P847 FINISHED
Object Kandava
Kandava is a small historic town in western Latvia known for its scenic location in the Kurzeme region and well-preserved old town architecture.
E1313434 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: Kandava | Statement: [Kurzeme, containsTown, Kandava]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kandava
Context triple: [Kurzeme, containsTown, Kandava]
  • A. Kudawa
    Kudawa is a village in Sri Lanka that serves as a primary gateway for visitors entering the Sinharaja Forest Reserve.
  • B. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of Papua New Guinea.
  • C. Kadaru
    Kadaru is a Nubian language spoken by the Kadaru people in parts of Sudan.
  • D. Kundagannada
    Kundagannada is a regional dialect of the Kannada language spoken primarily in the coastal districts of Karnataka, India.
  • E. Kandau
    Kandau is a town in present-day Latvia historically known as the birthplace of the German experimental psychologist Oswald Külpe.
  • 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: Kandava
Triple: [Kurzeme, containsTown, Kandava]
Generated description
Kandava is a small historic town in western Latvia known for its scenic location in the Kurzeme region and well-preserved old town architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kandava
Target entity description: Kandava is a small historic town in western Latvia known for its scenic location in the Kurzeme region and well-preserved old town architecture.
  • A. Kudawa
    Kudawa is a village in Sri Lanka that serves as a primary gateway for visitors entering the Sinharaja Forest Reserve.
  • B. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of Papua New Guinea.
  • C. Kadaru
    Kadaru is a Nubian language spoken by the Kadaru people in parts of Sudan.
  • D. Kundagannada
    Kundagannada is a regional dialect of the Kannada language spoken primarily in the coastal districts of Karnataka, India.
  • E. Kandau
    Kandau is a town in present-day Latvia historically known as the birthplace of the German experimental psychologist Oswald Külpe.
  • 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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f7e6fbac8190bf252c4337f50c29 completed April 19, 2026, 3:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03ac733e708190a7fde1fb61db5d5f completed May 12, 2026, 10:40 p.m.
NEDg Description generation batch_6a03ad2be6e0819081426da968a57db0 completed May 12, 2026, 10:43 p.m.
NED2 Entity disambiguation (via description) batch_6a03ad8898748190b57028bb2e2ed207 completed May 12, 2026, 10:45 p.m.
Created at: April 10, 2026, 10:33 a.m.