Triple

T19883489
Position Surface form Disambiguated ID Type / Status
Subject Sozopol E477835 entity
Predicate hasDistrict P459 FINISHED
Object Old Town
Old Town is the historic core of Sozopol, Bulgaria, known for its preserved traditional wooden houses, ancient ruins, and picturesque Black Sea views.
E1400087 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: Old Town | Statement: [Sozopol, hasDistrict, Old Town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Town
Context triple: [Sozopol, hasDistrict, Old Town]
  • A. Old Town
    Old Town is the medieval historic center of Kraków, renowned for its well-preserved architecture, bustling Main Market Square, and rich cultural heritage.
  • B. Old Town
    Old Town is the historic medieval heart of Edinburgh, Scotland, known for its narrow closes, iconic Royal Mile, and well-preserved architecture.
  • C. Old Town
    Old Town is a rustic, Western-style themed area within Thorpe Park featuring rides, attractions, and immersive scenery inspired by an old frontier town.
  • D. Old Town
    Old Town is the historic commercial and administrative center of Lilongwe, Malawi, known for its traditional markets, older architecture, and dense urban activity.
  • E. Old Town
    Old Town is the historic central district of Krosno, characterized by preserved architecture, cultural landmarks, and a traditional urban layout.
  • 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: Old Town
Triple: [Sozopol, hasDistrict, Old Town]
Generated description
Old Town is the historic core of Sozopol, Bulgaria, known for its preserved traditional wooden houses, ancient ruins, and picturesque Black Sea views.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Old Town
Target entity description: Old Town is the historic core of Sozopol, Bulgaria, known for its preserved traditional wooden houses, ancient ruins, and picturesque Black Sea views.
  • A. Old Town
    Old Town is the historic medieval center of Sospel, characterized by narrow cobbled streets, ancient stone buildings, and a preserved old-world atmosphere.
  • B. Old Town
    Old Town is the historic city center of Chernivtsi, known for its preserved architecture, cobblestone streets, and cultural landmarks reflecting the city’s multiethnic past.
  • C. Old Town
    Old Town is the historic central district of Sanok, Poland, known for its preserved architecture, cultural heritage, and traditional urban layout.
  • D. Old Town
    Old Town is the historic city center of Riga, Latvia, known for its medieval architecture, cobblestone streets, and UNESCO-listed cultural heritage.
  • E. Old Town
    Old Town is the historic waterfront district of Alexandria, Virginia, known for its preserved 18th- and 19th-century architecture, cobblestone streets, and vibrant shops and restaurants.
  • 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_69d8e51f32b08190b3687f4f60353250 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6590870908190a18b545f0ff0ccd6 completed April 20, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07dbcce4048190ba3b17c1dc4e1095 completed May 16, 2026, 2:51 a.m.
NEDg Description generation batch_6a07dccbcf788190bb03f396478b77f1 completed May 16, 2026, 2:56 a.m.
NED2 Entity disambiguation (via description) batch_6a07dd7f02d48190955d3b13a95b9c7e completed May 16, 2026, 2:59 a.m.
Created at: April 10, 2026, 1:52 p.m.