Triple
T8443154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lonsee |
E199598
|
entity |
| Predicate | hasNearbyCity |
P350
|
FINISHED |
| Object | Ulm |
E9969
|
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: Ulm | Statement: [Lonsee, hasNearbyCity, Ulm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ulm Context triple: [Lonsee, hasNearbyCity, Ulm]
-
A.
Ulm
chosen
Ulm is a historic city in the German state of Baden-Württemberg, best known for its towering Gothic cathedral and as the birthplace of physicist Albert Einstein.
-
B.
Heilbronn
Heilbronn is a city in the German state of Baden-Württemberg known for its industrial base, wine production, and role as a regional economic and educational hub.
-
C.
Augsburg
Augsburg is one of Germany’s oldest cities, a historic Bavarian center known for its rich Renaissance heritage and role as a major medieval trading hub.
-
D.
Neu-Ulm
Neu-Ulm is a Bavarian town in southern Germany located across the Danube River from the city of Ulm, forming a closely linked urban area with it.
-
E.
Günzburg
Günzburg is a small Bavarian town in southern Germany, historically notable as the birthplace of Nazi physician Josef Mengele.
- 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_69ca83170f9081909cd98f55614c6476 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe310d8e08190b871bda79acde678 |
completed | March 31, 2026, 3:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf5120159881908361bf9cb81e3932 |
completed | April 3, 2026, 5:33 a.m. |
Created at: March 30, 2026, 6:08 p.m.