Triple
T1863163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tempelhof-Schöneberg |
E34860
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Friedenau |
E107699
|
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: Friedenau | Statement: [Tempelhof-Schöneberg, contains, Friedenau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Friedenau Context triple: [Tempelhof-Schöneberg, contains, Friedenau]
-
A.
Friedenau
chosen
Friedenau is a residential district in southwestern Berlin known for its historic architecture, leafy streets, and literary heritage.
-
B.
Schaafheim
Schaafheim is a municipality in the state of Hesse in central Germany.
-
C.
Günsberg
Günsberg is a Swiss municipality located in the canton of Solothurn, known for its scenic setting near the Jura Mountains.
-
D.
Drensteinfurt
Drensteinfurt is a small town in North Rhine-Westphalia, Germany, known for its historic architecture and location in the Münsterland region.
-
E.
Rheydt
Rheydt is a district of the German city of Mönchengladbach in North Rhine-Westphalia, historically an independent town in the Rhineland.
- 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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb09f856c8190807a7cf2a5f49fcb |
completed | March 7, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae26f6e1288190a69d4197ce5bd5b1 |
completed | March 9, 2026, 1:48 a.m. |
Created at: March 4, 2026, 7:34 p.m.