Triple
T18281908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Мачва |
E437882
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object |
Дубока Јарак
Дубока Јарак је водоток у региону Мачве у западној Србији, познат као локална мања река/поток који одводњава околно пољопривредно подручје.
|
E1316020
|
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: Дубока Јарак | Statement: [Мачва, hasRiver, Дубока Јарак]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Дубока Јарак Context triple: [Мачва, hasRiver, Дубока Јарак]
-
A.
Doboka
Doboka is a town in the Nagaon district of Assam, India, known as a local commercial and transportation hub for the surrounding rural areas.
-
B.
Babreka
Babreka is one of Bulgaria’s famous Seven Rila Lakes, noted for its distinctive kidney-like shape and clear glacial waters in the Rila Mountains.
-
C.
Дьокуускай
Дьокуускай is the Sakha (Yakut) name for Yakutsk, the capital city of Russia’s Sakha Republic in northeastern Siberia.
-
D.
Rokovoj Bereg
Rokovoj Bereg is a climactic musical track from the Metal Gear Solid 3: Snake Eater soundtrack, associated with one of the game's most pivotal and emotional confrontations.
-
E.
Shijak
Shijak is a small town and municipality in western Albania, situated between the cities of Tirana and Durrës.
- 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: Дубока Јарак Triple: [Мачва, hasRiver, Дубока Јарак]
Generated description
Дубока Јарак је водоток у региону Мачве у западној Србији, познат као локална мања река/поток који одводњава околно пољопривредно подручје.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Дубока Јарак Target entity description: Дубока Јарак је водоток у региону Мачве у западној Србији, познат као локална мања река/поток који одводњава околно пољопривредно подручје.
-
A.
Doboka
Doboka is a town in the Nagaon district of Assam, India, known as a local commercial and transportation hub for the surrounding rural areas.
-
B.
Babreka
Babreka is one of Bulgaria’s famous Seven Rila Lakes, noted for its distinctive kidney-like shape and clear glacial waters in the Rila Mountains.
-
C.
Дьокуускай
Дьокуускай is the Sakha (Yakut) name for Yakutsk, the capital city of Russia’s Sakha Republic in northeastern Siberia.
-
D.
Rokovoj Bereg
Rokovoj Bereg is a climactic musical track from the Metal Gear Solid 3: Snake Eater soundtrack, associated with one of the game's most pivotal and emotional confrontations.
-
E.
Shijak
Shijak is a small town and municipality in western Albania, situated between the cities of Tirana and Durrës.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50056ea0481908d66bf263ac80c75 |
completed | April 19, 2026, 4:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03b4029cb88190963ae33570455c2d |
completed | May 12, 2026, 11:13 p.m. |
| NEDg | Description generation | batch_6a03b501b630819094c77aebf62081a2 |
completed | May 12, 2026, 11:17 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03b5c09f4881909fb0ead5fc48895c |
completed | May 12, 2026, 11:20 p.m. |
Created at: April 10, 2026, 10:35 a.m.