Triple
T7521675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Homburg vor der Höhe |
E177783
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object |
Bad Langensalza
Bad Langensalza is a historic spa town in Thuringia, Germany, known for its thermal baths, well-preserved old town, and numerous themed gardens.
|
E670174
|
NE FINISHED |
How this triple was built (4 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: Bad Langensalza | Statement: [Bad Homburg vor der Höhe, twinTown, Bad Langensalza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Langensalza Context triple: [Bad Homburg vor der Höhe, twinTown, Bad Langensalza]
-
A.
Bad Salzungen
Bad Salzungen is a spa town in Thuringia, Germany, known for its saline springs and therapeutic health resorts.
-
B.
Treuenbrietzen
Treuenbrietzen is a historic town in the German state of Brandenburg, known for its medieval architecture and role in Reformation-era history.
-
C.
Lülsfeld
Lülsfeld is a small municipality in the Schweinfurt district of Lower Franconia in northern Bavaria, Germany.
-
D.
Trakehnen
Trakehnen was a renowned East Prussian stud farm and village, historically famous as the cradle of the Trakehner horse breed.
-
E.
Langenberg
Langenberg is a prominent mountain in the Rothaargebirge range of Germany, known as the highest peak in the state of North Rhine-Westphalia.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bad Langensalza Triple: [Bad Homburg vor der Höhe, twinTown, Bad Langensalza]
Generated description
Bad Langensalza is a historic spa town in Thuringia, Germany, known for its thermal baths, well-preserved old town, and numerous themed gardens.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bad Langensalza Target entity description: Bad Langensalza is a historic spa town in Thuringia, Germany, known for its thermal baths, well-preserved old town, and numerous themed gardens.
-
A.
Bad Salzungen
Bad Salzungen is a spa town in Thuringia, Germany, known for its saline springs and therapeutic health resorts.
-
B.
Treuenbrietzen
Treuenbrietzen is a historic town in the German state of Brandenburg, known for its medieval architecture and role in Reformation-era history.
-
C.
Lülsfeld
Lülsfeld is a small municipality in the Schweinfurt district of Lower Franconia in northern Bavaria, Germany.
-
D.
Trakehnen
Trakehnen was a renowned East Prussian stud farm and village, historically famous as the cradle of the Trakehner horse breed.
-
E.
Langenberg
Langenberg is a prominent mountain in the Rothaargebirge range of Germany, known as the highest peak in the state of North Rhine-Westphalia.
- F. None of above. chosen
Provenance (5 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_69c69f29bf3081909a146aec7755f185 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f7c3c4c08190ad418978afcc98ec |
completed | March 27, 2026, 9:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84629f00c8190a64d51586bd3b96c |
completed | March 28, 2026, 9:20 p.m. |
| NEDg | Description generation | batch_69c8471da6c481909b48db7ad6e9426d |
completed | March 28, 2026, 9:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c848049f548190b8c9a9c3d3aeed45 |
completed | March 28, 2026, 9:28 p.m. |
Created at: March 27, 2026, 3:46 p.m.