Triple
T4797683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Úslava |
E106751
|
entity |
| Predicate | hasLeftTributary |
P415
|
FINISHED |
| Object |
Bradlava
Bradlava is a small river in the Czech Republic that serves as a left-bank tributary of the Úslava River.
|
E470899
|
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: Bradlava | Statement: [Úslava, hasLeftTributary, Bradlava]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bradlava Context triple: [Úslava, hasLeftTributary, Bradlava]
-
A.
Styggebrean
Styggebrean is a glacier located in Norway’s Jotunheimen mountain range, known for its rugged ice formations and alpine surroundings.
-
B.
Givlaari
Givlaari is an RNA interference-based therapy used to treat acute hepatic porphyria by reducing the production of toxic heme intermediates in the liver.
-
C.
Estwedus
Estwedus is the ancient name of the city now known as Aspendos, a prominent Greco-Roman settlement in Pamphylia, famed for its well-preserved Roman theater in modern-day Turkey.
-
D.
Fidra
Fidra is a small uninhabited island off the coast of East Lothian, Scotland, known for its lighthouse, seabird colonies, and as an inspiration for Robert Louis Stevenson.
-
E.
Gorg
Gorg is a neighborhood and metro/tram station area in Badalona, near Barcelona, known for its role as a local transport hub and residential district.
- 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: Bradlava Triple: [Úslava, hasLeftTributary, Bradlava]
Generated description
Bradlava is a small river in the Czech Republic that serves as a left-bank tributary of the Úslava River.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bradlava Target entity description: Bradlava is a small river in the Czech Republic that serves as a left-bank tributary of the Úslava River.
-
A.
Styggebrean
Styggebrean is a glacier located in Norway’s Jotunheimen mountain range, known for its rugged ice formations and alpine surroundings.
-
B.
Givlaari
Givlaari is an RNA interference-based therapy used to treat acute hepatic porphyria by reducing the production of toxic heme intermediates in the liver.
-
C.
Estwedus
Estwedus is the ancient name of the city now known as Aspendos, a prominent Greco-Roman settlement in Pamphylia, famed for its well-preserved Roman theater in modern-day Turkey.
-
D.
Fidra
Fidra is a small uninhabited island off the coast of East Lothian, Scotland, known for its lighthouse, seabird colonies, and as an inspiration for Robert Louis Stevenson.
-
E.
Gorg
Gorg is a neighborhood and metro/tram station area in Badalona, near Barcelona, known for its role as a local transport hub and residential district.
- 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_69bd43f591c881909e5a532388b0f3f3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6632708c8190b627d99363ab062c |
completed | March 20, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43f8d9548190857910be4ffc2711 |
completed | March 21, 2026, 7:08 a.m. |
| NEDg | Description generation | batch_69be46516cd881909144adabbe271907 |
completed | March 21, 2026, 7:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be47d4d26c8190a1a192dc12578f4f |
completed | March 21, 2026, 7:25 a.m. |
Created at: March 20, 2026, 1:22 p.m.