Triple

T4152909
Position Surface form Disambiguated ID Type / Status
Subject Lake Prespa E89947 entity
Predicate nearbyCity P350 FINISHED
Object Resen
Resen is a small town in southwestern North Macedonia that serves as the administrative and cultural center of the Prespa region near Lake Prespa.
 E417355 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: Resen | Statement: [Lake Prespa, nearbyCity, Resen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Resen
Context triple: [Lake Prespa, nearbyCity, Resen]
  • A. Romsa
    Romsa is the Northern Sami name for Tromsø, a major city in northern Norway known as a cultural and economic hub above the Arctic Circle.
  • B. Arrifes
    Arrifes is a civil parish in the municipality of Ponta Delgada on São Miguel Island in Portugal’s Azores archipelago.
  • C. Šolta
    Šolta is a small Croatian island in the Adriatic Sea, known for its tranquil villages, olive groves, and clear bays, located just off the coast from the city of Split.
  • D. Mora
    Mora is a town in central Sweden’s Dalarna region, known for its traditional Swedish culture, proximity to Lake Siljan, and as the finish line of the Vasaloppet cross-country ski race.
  • E. Mora
    Mora is a surname of Hungarian origin most notably borne by the German-Hungarian writer Terézia Mora.
  • 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: Resen
Triple: [Lake Prespa, nearbyCity, Resen]
Generated description
Resen is a small town in southwestern North Macedonia that serves as the administrative and cultural center of the Prespa region near Lake Prespa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Resen
Target entity description: Resen is a small town in southwestern North Macedonia that serves as the administrative and cultural center of the Prespa region near Lake Prespa.
  • A. Romsa
    Romsa is the Northern Sami name for Tromsø, a major city in northern Norway known as a cultural and economic hub above the Arctic Circle.
  • B. Arrifes
    Arrifes is a civil parish in the municipality of Ponta Delgada on São Miguel Island in Portugal’s Azores archipelago.
  • C. Šolta
    Šolta is a small Croatian island in the Adriatic Sea, known for its tranquil villages, olive groves, and clear bays, located just off the coast from the city of Split.
  • D. Mora
    Mora is a surname of Hungarian origin most notably borne by the German-Hungarian writer Terézia Mora.
  • E. Mora
    Mora is a town in central Sweden’s Dalarna region, known for its traditional Swedish culture, proximity to Lake Siljan, and as the finish line of the Vasaloppet cross-country ski race.
  • 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_69aed95a59a881909b26e70b42c6811a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0277a910819085cde5df9a8110d8 completed March 9, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f399c748190a87ca2a824dbfbca completed March 14, 2026, 3:31 p.m.
NEDg Description generation batch_69b580260a588190a2e1a84513a8c72f completed March 14, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_69b580c46e7481908aa13c6d7c6e36de completed March 14, 2026, 3:37 p.m.
Created at: March 9, 2026, 3:44 p.m.