Triple

T21290008
Position Surface form Disambiguated ID Type / Status
Subject Sarca River E524760 entity
Predicate mouthLocation P417 FINISHED
Object Torbole
Torbole is a picturesque village on the northern shore of Italy’s Lake Garda, known for its windsurfing, sailing, and scenic lakeside setting.
 E1476518 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: Torbole | Statement: [Sarca River, mouthLocation, Torbole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Torbole
Context triple: [Sarca River, mouthLocation, Torbole]
  • A. Thoseghar
    Thoseghar is a small village in Maharashtra, India, known primarily as the access point to the scenic Thoseghar Waterfalls and surrounding hilly countryside.
  • B. Katargam
    Katargam is a prominent residential and industrial suburb in the city of Surat, Gujarat, known especially for its diamond and textile industries.
  • C. Meʼen
    Meʼen is an Afroasiatic Surmic language spoken primarily by the Meʼen people of southwestern Ethiopia.
  • D. Hamra
    Hamra is a vibrant, cosmopolitan neighborhood in Beirut, Lebanon, known for its bustling commercial streets, cafes, and cultural life.
  • E. Turtusha
    Turtusha is the historical Arabic name for the city of Tortosa in Catalonia, Spain, which was an important medieval port and cultural 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: Torbole
Triple: [Sarca River, mouthLocation, Torbole]
Generated description
Torbole is a picturesque village on the northern shore of Italy’s Lake Garda, known for its windsurfing, sailing, and scenic lakeside setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Torbole
Target entity description: Torbole is a picturesque village on the northern shore of Italy’s Lake Garda, known for its windsurfing, sailing, and scenic lakeside setting.
  • A. Thoseghar
    Thoseghar is a small village in Maharashtra, India, known primarily as the access point to the scenic Thoseghar Waterfalls and surrounding hilly countryside.
  • B. Katargam
    Katargam is a prominent residential and industrial suburb in the city of Surat, Gujarat, known especially for its diamond and textile industries.
  • C. Meʼen
    Meʼen is an Afroasiatic Surmic language spoken primarily by the Meʼen people of southwestern Ethiopia.
  • D. Hamra
    Hamra is a vibrant, cosmopolitan neighborhood in Beirut, Lebanon, known for its bustling commercial streets, cafes, and cultural life.
  • E. Turtusha
    Turtusha is the historical Arabic name for the city of Tortosa in Catalonia, Spain, which was an important medieval port and cultural 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736d9467881908ec5b1dec76e6f5d completed April 21, 2026, 8:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09980e17f0819087ae4fd3712fb584 completed May 17, 2026, 10:27 a.m.
NEDg Description generation batch_6a0998d6b37881908a1b09afc1f67746 completed May 17, 2026, 10:30 a.m.
NED2 Entity disambiguation (via description) batch_6a0999884e0481909b7ea54cd7ef87b5 completed May 17, 2026, 10:33 a.m.
Created at: April 16, 2026, 4:03 p.m.