Triple
T23028136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mehlem |
E573379
|
entity |
| Predicate | hasLandmarkView |
P9193
|
FINISHED |
| Object | Drachenfels |
—
|
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: Drachenfels | Statement: [Mehlem, hasLandmarkView, Drachenfels]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drachenfels Context triple: [Mehlem, hasLandmarkView, Drachenfels]
-
A.
Drachenfels
chosen
Drachenfels is a prominent hill on the Rhine in western Germany, famed for its ruined castle, scenic views, and association with legends such as the Nibelungen saga.
-
B.
Falkenfels
Falkenfels is a small municipality in the district of Straubing-Bogen in the Bavarian region of Germany.
-
C.
Königsstuhl von Rhens
Der Königsstuhl von Rhens ist ein historischer steinerner Königswahl- und Versammlungsplatz am Rhein, an dem im Mittelalter deutsche Könige und Kaiser feierlich anerkannt wurden.
-
D.
Wartenfels
Wartenfels is a locality within the municipality of Thalgau in the Austrian state of Salzburg, known for its scenic surroundings and nearby castle ruins.
-
E.
Hardtberg
Hardtberg is a borough of the German city of Bonn, located in the western part of the city and comprising several residential and administrative districts.
- 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_69e245b821008190b0e09cb02092aae1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1847f453881909a8f2affb48c64f1 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:52 p.m.