Triple

T4063968
Position Surface form Disambiguated ID Type / Status
Subject Riga City Hall E86280 entity
Predicate locatedInOldTown P40 FINISHED
Object Vecrīga
Vecrīga is the historic old town of Riga, Latvia, known for its medieval architecture, cobblestone streets, and status as a UNESCO World Heritage Site.
 E410066 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: Vecrīga | Statement: [Riga City Hall, locatedInOldTown, Vecrīga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vecrīga
Context triple: [Riga City Hall, locatedInOldTown, Vecrīga]
  • A. Vidzeme
    Vidzeme is a historical region in northern Latvia known for its rich cultural heritage, forests, and role in the development of Latvian national identity.
  • B. Vardzia
    Vardzia is a medieval cave monastery complex in southern Georgia, renowned for its extensive rock-cut dwellings and frescoed church.
  • C. Veklury
    Veklury is the brand name for remdesivir, an antiviral medication used primarily to treat COVID-19.
  • D. Idvies
    Idvies is a small rural village located within the Angus council area in eastern Scotland.
  • E. Rausu
    Rausu is a small coastal town on Japan’s Shiretoko Peninsula, known for its rich marine wildlife, drift ice sightseeing, and access to the remote natural landscapes of eastern Hokkaido.
  • 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: Vecrīga
Triple: [Riga City Hall, locatedInOldTown, Vecrīga]
Generated description
Vecrīga is the historic old town of Riga, Latvia, known for its medieval architecture, cobblestone streets, and status as a UNESCO World Heritage Site.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vecrīga
Target entity description: Vecrīga is the historic old town of Riga, Latvia, known for its medieval architecture, cobblestone streets, and status as a UNESCO World Heritage Site.
  • A. Vidzeme
    Vidzeme is a historical region in northern Latvia known for its rich cultural heritage, forests, and role in the development of Latvian national identity.
  • B. Vardzia
    Vardzia is a medieval cave monastery complex in southern Georgia, renowned for its extensive rock-cut dwellings and frescoed church.
  • C. Veklury
    Veklury is the brand name for remdesivir, an antiviral medication used primarily to treat COVID-19.
  • D. Idvies
    Idvies is a small rural village located within the Angus council area in eastern Scotland.
  • E. Rausu
    Rausu is a small coastal town on Japan’s Shiretoko Peninsula, known for its rich marine wildlife, drift ice sightseeing, and access to the remote natural landscapes of eastern Hokkaido.
  • 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_69aed93c69208190a4efac0efe3cd69b completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbd7896c81909c61ed0d910d9c5f completed March 9, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562ae949c819092affaaca97c16d1 completed March 14, 2026, 1:29 p.m.
NEDg Description generation batch_69b5633103e081909dbe7a7e54877343 completed March 14, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_69b563eca17c81908deff0d361a7be87 completed March 14, 2026, 1:34 p.m.
Created at: March 9, 2026, 3:38 p.m.