Triple
T624295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harz |
E14581
|
entity |
| Predicate | hasRiverSource |
P947
|
FINISHED |
| Object |
Selke
The Selke is a river in central Germany that flows through the Harz Mountains and Saxony-Anhalt, known for its scenic valleys and historic towns along its course.
|
E78850
|
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: Selke | Statement: [Harz, hasRiverSource, Selke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Selke Context triple: [Harz, hasRiverSource, Selke]
-
A.
Jaakko
Jaakko is a Finnish given name, equivalent to the English name James.
-
B.
Salla
Salla is a sparsely populated municipality in northeastern Finland, known for its remote wilderness landscapes and history of territorial changes during the Winter War and World War II.
-
C.
Seurasaarenselkä
Seurasaarenselkä is a bay area of the Baltic Sea in Helsinki, Finland, known for its coastal scenery and proximity to several notable city landmarks and recreational areas.
-
D.
Svante
Svante is the given name of Swedish geneticist Svante Pääbo, a Nobel Prize–winning pioneer in the field of paleogenomics.
-
E.
Helleren
Helleren is a small historic settlement in Norway known for its traditional houses built under a large rock overhang near the Jøssingfjord.
- 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: Selke Triple: [Harz, hasRiverSource, Selke]
Generated description
The Selke is a river in central Germany that flows through the Harz Mountains and Saxony-Anhalt, known for its scenic valleys and historic towns along its course.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Selke Target entity description: The Selke is a river in central Germany that flows through the Harz Mountains and Saxony-Anhalt, known for its scenic valleys and historic towns along its course.
-
A.
Jaakko
Jaakko is a Finnish given name, equivalent to the English name James.
-
B.
Salla
Salla is a sparsely populated municipality in northeastern Finland, known for its remote wilderness landscapes and history of territorial changes during the Winter War and World War II.
-
C.
Seurasaarenselkä
Seurasaarenselkä is a bay area of the Baltic Sea in Helsinki, Finland, known for its coastal scenery and proximity to several notable city landmarks and recreational areas.
-
D.
Svante
Svante is the given name of Swedish geneticist Svante Pääbo, a Nobel Prize–winning pioneer in the field of paleogenomics.
-
E.
Helleren
Helleren is a small historic settlement in Norway known for its traditional houses built under a large rock overhang near the Jøssingfjord.
- 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a514b514819088e7b6b7e4675905 |
completed | March 1, 2026, 8:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a56935ec748190984b9cb6add6b700 |
completed | March 2, 2026, 10:40 a.m. |
| NEDg | Description generation | batch_69a569d5f2a081908f63ce6755b2994c |
completed | March 2, 2026, 10:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a56b2283dc8190b252595b5bb394f3 |
completed | March 2, 2026, 10:49 a.m. |
Created at: March 1, 2026, 7:35 p.m.