Triple

T2744106
Position Surface form Disambiguated ID Type / Status
Subject Struma E60823 entity
Predicate passesNear P416 FINISHED
Object Sandanski
Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
 E294571 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: Sandanski | Statement: [Struma, passesNear, Sandanski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sandanski
Context triple: [Struma, passesNear, Sandanski]
  • A. Varna
    Varna is a major Bulgarian city on the Black Sea coast known as an important economic, cultural, and maritime center.
  • B. Silistra
    Silistra is a historic city in northeastern Bulgaria on the Danube River, known as an important cultural and economic center of the Dobruja region.
  • C. Bansko
    Bansko is a Bulgarian mountain town renowned as one of Eastern Europe’s leading ski and winter sports resorts.
  • D. Pliska
    Pliska was the first capital city of the early medieval First Bulgarian Empire, serving as its political and administrative center.
  • E. Balchik
    Balchik is a coastal town and resort on the Black Sea in northeastern Bulgaria, known for its picturesque cliffs, botanical garden, and the former Romanian Queen Marie’s palace.
  • 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: Sandanski
Triple: [Struma, passesNear, Sandanski]
Generated description
Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sandanski
Target entity description: Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
  • A. Varna
    Varna is a major Bulgarian city on the Black Sea coast known as an important economic, cultural, and maritime center.
  • B. Silistra
    Silistra is a historic city in northeastern Bulgaria on the Danube River, known as an important cultural and economic center of the Dobruja region.
  • C. Bansko
    Bansko is a Bulgarian mountain town renowned as one of Eastern Europe’s leading ski and winter sports resorts.
  • D. Pliska
    Pliska was the first capital city of the early medieval First Bulgarian Empire, serving as its political and administrative center.
  • E. Balchik
    Balchik is a coastal town and resort on the Black Sea in northeastern Bulgaria, known for its picturesque cliffs, botanical garden, and the former Romanian Queen Marie’s palace.
  • 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_69ab4b79846081909096725374d65ce9 completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdb32ef74819096ae399d16d4f31d completed March 7, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69afbbcebe788190aa2b40158b64b7b2 completed March 10, 2026, 6:35 a.m.
NEDg Description generation batch_69afbceb981c819095038ac01d98fb45 completed March 10, 2026, 6:40 a.m.
NED2 Entity disambiguation (via description) batch_69afbd5e28f481909d82e42c33e4ef86 completed March 10, 2026, 6:42 a.m.
Created at: March 6, 2026, 9:56 p.m.