Triple

T12034554
Position Surface form Disambiguated ID Type / Status
Subject Emajõgi River E286500 entity
Predicate hasBridge P386 FINISHED
Object Vabadussild
Vabadussild is a bridge in Tartu, Estonia, spanning the Emajõgi River and serving as a key pedestrian and traffic crossing in the city.
 E960789 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: Vabadussild | Statement: [Emajõgi River, hasBridge, Vabadussild]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vabadussild
Context triple: [Emajõgi River, hasBridge, Vabadussild]
  • A. Horgabost
    Horgabost is a small coastal settlement on the Isle of Harris in Scotland’s Outer Hebrides, known for its scenic beaches and rugged island landscape.
  • B. Gullaug
    Gullaug is a small settlement in the municipality of Lier in Viken county, Norway, known for its residential character and proximity to the Drammen region.
  • C. Heltermaa
    Heltermaa is a small port village on the eastern coast of Hiiumaa Island in Estonia, serving as a key ferry connection to the mainland.
  • D. Seskarö
    Seskarö is a Swedish island in the northern Baltic Sea known for its forests, beaches, and traditional fishing and forestry communities.
  • E. Lögberg
    Lögberg is the historic Law Rock at Þingvellir in Iceland, where the Althing, one of the world’s oldest parliaments, traditionally convened and laws were proclaimed.
  • 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: Vabadussild
Triple: [Emajõgi River, hasBridge, Vabadussild]
Generated description
Vabadussild is a bridge in Tartu, Estonia, spanning the Emajõgi River and serving as a key pedestrian and traffic crossing in the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vabadussild
Target entity description: Vabadussild is a bridge in Tartu, Estonia, spanning the Emajõgi River and serving as a key pedestrian and traffic crossing in the city.
  • A. Horgabost
    Horgabost is a small coastal settlement on the Isle of Harris in Scotland’s Outer Hebrides, known for its scenic beaches and rugged island landscape.
  • B. Gullaug
    Gullaug is a small settlement in the municipality of Lier in Viken county, Norway, known for its residential character and proximity to the Drammen region.
  • C. Heltermaa
    Heltermaa is a small port village on the eastern coast of Hiiumaa Island in Estonia, serving as a key ferry connection to the mainland.
  • D. Seskarö
    Seskarö is a Swedish island in the northern Baltic Sea known for its forests, beaches, and traditional fishing and forestry communities.
  • E. Lögberg
    Lögberg is the historic Law Rock at Þingvellir in Iceland, where the Althing, one of the world’s oldest parliaments, traditionally convened and laws were proclaimed.
  • 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_69d6ab4669e48190b59246358b0383ab completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d90408cbf0819093270c9833ef149a completed April 10, 2026, 2:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69f49d6ec4b8819093ff50254a851444 completed May 1, 2026, 12:32 p.m.
NEDg Description generation batch_69f53d930714819080f92d223d930389 completed May 1, 2026, 11:56 p.m.
NED2 Entity disambiguation (via description) batch_69f56505c0b481909f9caaf338f73033 completed May 2, 2026, 2:44 a.m.
Created at: April 8, 2026, 9:47 p.m.