Triple
T16371643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Most |
E397576
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Marienberg |
E84126
|
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: Marienberg | Statement: [Most, hasTwinTown, Marienberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marienberg Context triple: [Most, hasTwinTown, Marienberg]
-
A.
Marienberg
chosen
Marienberg is a historic mining town in Saxony, Germany, known for its Renaissance-era planned layout and location in the central Ore Mountains.
-
B.
Marienberg hill
Marienberg hill is a prominent elevation overlooking Würzburg, Germany, best known as the site of the historic Marienberg Fortress.
-
C.
Falkenfels
Falkenfels is a small municipality in the district of Straubing-Bogen in the Bavarian region of Germany.
-
D.
Riffelberg
Riffelberg is a scenic mountain stop in the Swiss Alps near Zermatt, known for its panoramic views of the Matterhorn and surrounding peaks.
-
E.
Marienberg Fortress
Marienberg Fortress is a historic hilltop castle complex overlooking Würzburg, Germany, known for its medieval fortifications and panoramic views of the Main River valley.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2ff420d04819096ff12e08edf2f8b |
completed | April 18, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c522a7c8190a306b85354a087fd |
completed | May 10, 2026, 8:05 a.m. |
Created at: April 10, 2026, 5:08 a.m.