Triple
T17363385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bismarck Tower Heidelberg |
E422125
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Heiligenberg |
—
|
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: Heiligenberg | Statement: [Bismarck Tower Heidelberg, locatedOn, Heiligenberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heiligenberg Context triple: [Bismarck Tower Heidelberg, locatedOn, Heiligenberg]
-
A.
Heiligenberg
chosen
Heiligenberg is a prominent hill overlooking Heidelberg in Germany, known for its historical ruins and cultural sites.
-
B.
Hermannsberg
Hermannsberg is a location in Germany known, among other things, as the place where the influential German educator Kurt Hahn died.
-
C.
Hünenberg
Hünenberg is a municipality in the canton of Zug in central Switzerland, known for its residential character and location near Lake Zug.
-
D.
Eibenberg
Eibenberg is a small locality that forms one of the subdivisions of the municipality of Burkhardtsdorf in Saxony, Germany.
-
E.
Johannisberg
Johannisberg is a renowned wine-growing area in Germany’s Rheingau region, historically famous for its high-quality Riesling wines.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4e3c3481909dfaa00334c5010e |
completed | April 19, 2026, 2:13 a.m. |
Created at: April 10, 2026, 5:44 a.m.