Triple
T2938246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oker |
E79320
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Harz |
E14581
|
NE FINISHED |
How this triple was built (2 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: Harz | Statement: [Oker, region, Harz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harz Context triple: [Oker, region, Harz]
-
A.
Harz
chosen
Harz is a low mountain range in central Germany known for its dense forests, mining history, and association with German folklore such as the Brocken and Walpurgis Night.
-
B.
Rhön
Rhön is a low mountain range in central Germany known for its volcanic landscape, open plateaus, and designation as a UNESCO Biosphere Reserve.
-
C.
Thuringian Forest
The Thuringian Forest is a low mountain range in central Germany known for its dense woodlands, scenic hiking trails, and the historic Rennsteig ridgeway.
-
D.
Herzberg am Harz
Herzberg am Harz is a small town in Lower Saxony, Germany, located on the southern edge of the Harz Mountains and known for its historic castle and timber-framed architecture.
-
E.
Franconian Forest
The Franconian Forest is a low mountain range in northern Bavaria, Germany, known for its extensive woodlands, hiking trails, and role as a watershed between the Main and Saale river systems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ad8b0fbab081908f6a61567c045d8d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad986c1c0c8190a6a9f17082438cfd |
completed | March 8, 2026, 3:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b224a78bbc8190b4f4cdb058d5a176 |
completed | March 12, 2026, 2:27 a.m. |
Created at: March 8, 2026, 2:56 p.m.