Triple

T2965290
Position Surface form Disambiguated ID Type / Status
Subject Girona E80146 entity
Predicate locatedOnRiver P165 FINISHED
Object Onyar
The Onyar is a river in the city of Girona, Spain, known for the picturesque row of colorful houses lining its banks and the iconic bridges that cross it.
 E315237 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: Onyar | Statement: [Girona, locatedOnRiver, Onyar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Onyar
Context triple: [Girona, locatedOnRiver, Onyar]
  • A. Kamiros
    Kamiros is an ancient city and archaeological site on the northwest coast of Rhodes, known for its well-preserved Hellenistic ruins and grid-planned layout.
  • B. Damrak
    Damrak is a central street and canal in Amsterdam that runs from Amsterdam Centraal Station toward Dam Square, forming one of the city’s main tourist and commercial arteries.
  • C. Kalloni
    Kalloni is a town on the Greek island of Lesbos, known for its large bay, salt pans, and rich birdlife.
  • D. Mora
    Mora is a surname of Hungarian origin most notably borne by the German-Hungarian writer Terézia Mora.
  • E. Korydallos
    Korydallos is a densely populated suburban municipality in the western part of the Athens urban area in Greece, known for its residential character and major prison facility.
  • 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: Onyar
Triple: [Girona, locatedOnRiver, Onyar]
Generated description
The Onyar is a river in the city of Girona, Spain, known for the picturesque row of colorful houses lining its banks and the iconic bridges that cross it.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Onyar
Target entity description: The Onyar is a river in the city of Girona, Spain, known for the picturesque row of colorful houses lining its banks and the iconic bridges that cross it.
  • A. Kamiros
    Kamiros is an ancient city and archaeological site on the northwest coast of Rhodes, known for its well-preserved Hellenistic ruins and grid-planned layout.
  • B. Damrak
    Damrak is a central street and canal in Amsterdam that runs from Amsterdam Centraal Station toward Dam Square, forming one of the city’s main tourist and commercial arteries.
  • C. Kalloni
    Kalloni is a town on the Greek island of Lesbos, known for its large bay, salt pans, and rich birdlife.
  • D. Mora
    Mora is a surname of Hungarian origin most notably borne by the German-Hungarian writer Terézia Mora.
  • E. Korydallos
    Korydallos is a densely populated suburban municipality in the western part of the Athens urban area in Greece, known for its residential character and major prison facility.
  • 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_69ad8b1341848190bd19dbf46892887d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad995a28e88190a4d6b9ef2c0d8e61 completed March 8, 2026, 3:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0fc9bc190819087cb35ee7c78825a completed March 11, 2026, 5:24 a.m.
NEDg Description generation batch_69b0fd25e07c819088b2b1bcef4cf54e completed March 11, 2026, 5:27 a.m.
NED2 Entity disambiguation (via description) batch_69b100ecbee081908832ddec0efdc751 completed March 11, 2026, 5:43 a.m.
Created at: March 8, 2026, 2:58 p.m.