Triple
T8877315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schwarmstedt |
E211319
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Heidekreis |
E164519
|
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: Heidekreis | Statement: [Schwarmstedt, partOf, Heidekreis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heidekreis Context triple: [Schwarmstedt, partOf, Heidekreis]
-
A.
Heidekreis
chosen
Heidekreis is a rural district in Lower Saxony, Germany, known for its heath landscapes, nature reserves, and historic sites.
-
B.
Harzheim
Harzheim is a village in the town of Mechernich in North Rhine-Westphalia, Germany.
-
C.
Hagen am Teutoburger Wald
Hagen am Teutoburger Wald is a small municipality in Lower Saxony, Germany, situated near the Teutoburg Forest and close to the city of Osnabrück.
-
D.
Kellerwald
Kellerwald is a low mountain forest region in central Germany known for its ancient beech woodlands and protected national park status.
-
E.
Gandersheim
Gandersheim is a historic town in present-day Lower Saxony, Germany, best known for its medieval abbey and role as a cultural and religious center in the early Holy Roman Empire.
- 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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61496870819097c55c73aca62aac |
completed | April 1, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1c641048190aabbc10f461099f4 |
completed | April 3, 2026, 1:33 p.m. |
Created at: March 30, 2026, 6:52 p.m.