Triple

T8769053
Position Surface form Disambiguated ID Type / Status
Subject Governorate of Courland E208409 entity
Predicate majorCity P316 FINISHED
Object Tukums
Tukums is a historic town in western Latvia known for its medieval heritage, role as a regional trade center, and proximity to the Gulf of Riga.
E756081 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: Tukums | Statement: [Governorate of Courland, majorCity, Tukums]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tukums
Context triple: [Governorate of Courland, majorCity, Tukums]
  • A. Tuhelj
    Tuhelj is a small municipality in northern Croatia known for its thermal spa resort and rural surroundings.
  • B. Tyto
    Tyto is a genus of medium-sized owls best known for including the widespread barn owl and its close relatives.
  • C. Togninia
    Togninia is a genus of fungi known for its ascomycetous species, some of which are associated with plant diseases.
  • D. Tuineje
    Tuineje is a coastal municipality on the island of Fuerteventura in Spain’s Canary Islands, known for its rural landscapes, beaches, and traditional Canarian culture.
  • E. Tegüder
    Tegüder (also known as Ahmad Tegüder) was a 13th-century Ilkhanid ruler of Persia who converted to Islam and briefly reigned as a Mongol khan.
  • 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: Tukums
Triple: [Governorate of Courland, majorCity, Tukums]
Generated description
Tukums is a historic town in western Latvia known for its medieval heritage, role as a regional trade center, and proximity to the Gulf of Riga.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tukums
Target entity description: Tukums is a historic town in western Latvia known for its medieval heritage, role as a regional trade center, and proximity to the Gulf of Riga.
  • A. Tuhelj
    Tuhelj is a small municipality in northern Croatia known for its thermal spa resort and rural surroundings.
  • B. Tyto
    Tyto is a genus of medium-sized owls best known for including the widespread barn owl and its close relatives.
  • C. Togninia
    Togninia is a genus of fungi known for its ascomycetous species, some of which are associated with plant diseases.
  • D. Tuineje
    Tuineje is a coastal municipality on the island of Fuerteventura in Spain’s Canary Islands, known for its rural landscapes, beaches, and traditional Canarian culture.
  • E. Tegüder
    Tegüder (also known as Ahmad Tegüder) was a 13th-century Ilkhanid ruler of Persia who converted to Islam and briefly reigned as a Mongol khan.
  • 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_69ca835edb4481909b4aafb616dc5eb7 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5eec49708190ba760d81a7974c50 completed March 31, 2026, 11:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf51af01e48190af674a03d0768f3b completed April 3, 2026, 5:35 a.m.
NEDg Description generation batch_69cf5291147481908179e75547cf981d completed April 3, 2026, 5:39 a.m.
NED2 Entity disambiguation (via description) batch_69cf5331475c8190b3e8c565f0be7dfd completed April 3, 2026, 5:42 a.m.
Created at: March 30, 2026, 6:41 p.m.