Triple
T19592784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carillon Berlin |
E470276
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Großer Tiergarten |
—
|
NE NERFINISHED |
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: Großer Tiergarten | Statement: [Carillon Berlin, near, Großer Tiergarten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Großer Tiergarten Context triple: [Carillon Berlin, near, Großer Tiergarten]
-
A.
Großer Tiergarten park
Großer Tiergarten park is a large, historic urban park in central Berlin known for its wooded landscapes, lakes, and cultural landmarks.
-
B.
Tiergarten park
Tiergarten park is a historic public park in the German town of Kleve, known for its landscaped grounds, walking paths, and recreational green spaces.
-
C.
Tiergarten
chosen
Tiergarten is a large central park in Berlin known for its expansive green spaces, monuments, and cultural landmarks.
-
D.
Volkspark Friedrichshain
Volkspark Friedrichshain is a large historic public park in Berlin known for its wooded hills, walking paths, and recreational facilities.
-
E.
Friedrichspark
Friedrichspark is a park area in Mannheim, Germany, known historically for hosting the Eisstadion am Friedrichspark ice stadium and serving as a local recreational space.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64057460c8190962e2e58f06b3985 |
completed | April 20, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:43 p.m.