Triple

T1559716
Position Surface form Disambiguated ID Type / Status
Subject Gulf of Riga E33290 entity
Predicate majorPort P528 FINISHED
Object Pärnu
Pärnu is a coastal city in southwestern Estonia known as a popular summer resort and spa destination on the Baltic Sea.
 E180225 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: Pärnu | Statement: [Gulf of Riga, majorPort, Pärnu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pärnu
Context triple: [Gulf of Riga, majorPort, Pärnu]
  • A. Tartu
    Tartu is Estonia’s second-largest city and a historic cultural and intellectual center, best known as the country’s main university town.
  • B. Viedma
    Viedma is a city in northern Patagonia and one of the oldest settlements in Argentina, serving as the capital of Río Negro Province.
  • C. Kuressaare
    Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
  • D. Jelgava
    Jelgava is a city in central Latvia known for its historic Jelgava Palace and role as a regional cultural and educational center.
  • E. Ventspils
    Ventspils is a port city on Latvia’s Baltic Sea coast known for its major ice-free harbor, oil and cargo terminals, and well-preserved historic center.
  • 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: Pärnu
Triple: [Gulf of Riga, majorPort, Pärnu]
Generated description
Pärnu is a coastal city in southwestern Estonia known as a popular summer resort and spa destination on the Baltic Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pärnu
Target entity description: Pärnu is a coastal city in southwestern Estonia known as a popular summer resort and spa destination on the Baltic Sea.
  • A. Tartu
    Tartu is Estonia’s second-largest city and a historic cultural and intellectual center, best known as the country’s main university town.
  • B. Viedma
    Viedma is a city in northern Patagonia and one of the oldest settlements in Argentina, serving as the capital of Río Negro Province.
  • C. Kuressaare
    Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
  • D. Jelgava
    Jelgava is a city in central Latvia known for its historic Jelgava Palace and role as a regional cultural and educational center.
  • E. Ventspils
    Ventspils is a port city on Latvia’s Baltic Sea coast known for its major ice-free harbor, oil and cargo terminals, and well-preserved historic center.
  • 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_69a885ef9cf48190b0af0f5ce3d02231 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90885d6208190b4b7d6ad336d4d16 completed March 5, 2026, 4:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad4691cf5081909768f619b7a8a940 completed March 8, 2026, 9:51 a.m.
NEDg Description generation batch_69ad470069f08190b886041d1a1c7707 completed March 8, 2026, 9:53 a.m.
NED2 Entity disambiguation (via description) batch_69ad475d9528819086546aae6db74e19 completed March 8, 2026, 9:54 a.m.
Created at: March 4, 2026, 7:27 p.m.