Triple
T7966042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colditz |
E185207
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Zwickauer Mulde |
E392701
|
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: Zwickauer Mulde | Statement: [Colditz, locatedOnRiver, Zwickauer Mulde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zwickauer Mulde Context triple: [Colditz, locatedOnRiver, Zwickauer Mulde]
-
A.
River Mulde
The River Mulde is a river in central Germany that flows through the states of Saxony and Saxony-Anhalt before joining the Elbe.
-
B.
Freiberger Mulde
chosen
The Freiberger Mulde is a river in Saxony, Germany, that originates in the Ore Mountains and flows northward to help form the Mulde River.
-
C.
Wakenitz
Wakenitz is a river in northern Germany that flows through the city of Lübeck and connects the Ratzeburger See to the Trave River.
-
D.
Peene River
The Peene River is a lowland river in northeastern Germany, often called the "Amazon of the North" for its largely untouched wetlands and rich biodiversity.
-
E.
Unstrut River
The Unstrut River is a tributary of the Saale in central Germany, flowing through Thuringia and Saxony-Anhalt and known for its scenic valleys, vineyards, and historic towns.
- 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_69ca8297699481909b75a405f01e03af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ba262208190887169fe94e47b0e |
completed | March 31, 2026, 3:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc63552ec8190bbcae99d48b5f763 |
completed | April 2, 2026, 1:28 a.m. |
Created at: March 30, 2026, 5:12 p.m.