Triple

T5992118
Position Surface form Disambiguated ID Type / Status
Subject Liepāja E133373 entity
Predicate hasDistrict P459 FINISHED
Object Karosta
Karosta is a historic former military port district in the Latvian city of Liepāja, known for its Tsarist-era fortifications, Soviet naval heritage, and distinctive coastal landscape.
 E562333 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: Karosta | Statement: [Liepāja, hasDistrict, Karosta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Karosta
Context triple: [Liepāja, hasDistrict, Karosta]
  • A. Somero
    Somero is a small town and municipality in southwestern Finland known for its rural landscapes and agricultural heritage.
  • B. Mahuva
    Mahuva is a coastal town in Gujarat, India, known for its onion production, coconut plantations, and scenic beaches along the Arabian Sea.
  • C. Hvalba
    Hvalba is a village on the Faroe Islands' southernmost island of Suðuroy, known for its historic coal mining and scenic coastal landscape.
  • D. Ormur
    Ormur is a lesser-known Eastern Iranian language spoken primarily by the Ormur people in parts of Afghanistan and Pakistan.
  • E. Ylla
    Ylla is a short story by Ray Bradbury, set on Mars and exploring the inner life and unfulfilled desires of a Martian woman.
  • 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: Karosta
Triple: [Liepāja, hasDistrict, Karosta]
Generated description
Karosta is a historic former military port district in the Latvian city of Liepāja, known for its Tsarist-era fortifications, Soviet naval heritage, and distinctive coastal landscape.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Karosta
Target entity description: Karosta is a historic former military port district in the Latvian city of Liepāja, known for its Tsarist-era fortifications, Soviet naval heritage, and distinctive coastal landscape.
  • A. Somero
    Somero is a small town and municipality in southwestern Finland known for its rural landscapes and agricultural heritage.
  • B. Mahuva
    Mahuva is a coastal town in Gujarat, India, known for its onion production, coconut plantations, and scenic beaches along the Arabian Sea.
  • C. Hvalba
    Hvalba is a village on the Faroe Islands' southernmost island of Suðuroy, known for its historic coal mining and scenic coastal landscape.
  • D. Ormur
    Ormur is a lesser-known Eastern Iranian language spoken primarily by the Ormur people in parts of Afghanistan and Pakistan.
  • E. Ylla
    Ylla is a short story by Ray Bradbury, set on Mars and exploring the inner life and unfulfilled desires of a Martian woman.
  • 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_69c0087010d081908bb8142342d63330 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04e8fd030819095a4f3b3d425ec21 completed March 22, 2026, 8:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c10861c0bc8190b6290d7363f4264a completed March 23, 2026, 9:31 a.m.
NEDg Description generation batch_69c10c44b6408190be8bc1d96e0db2e4 completed March 23, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_69c10cd7c1c8819085ec8bee7f42afc4 completed March 23, 2026, 9:50 a.m.
Created at: March 22, 2026, 4:05 p.m.