Triple
T22435487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ortsbezirk 6 Frankfurt am Main |
E554610
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Sossenheim |
—
|
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: Sossenheim | Statement: [Ortsbezirk 6 Frankfurt am Main, contains, Sossenheim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sossenheim Context triple: [Ortsbezirk 6 Frankfurt am Main, contains, Sossenheim]
-
A.
Sossenheim
chosen
Sossenheim is a district in the west of Frankfurt am Main, Germany, known for its residential character and proximity to the Main River industrial areas.
-
B.
Sporkenheim
Sporkenheim is a district or locality within the town of Ingelheim am Rhein in Rhineland-Palatinate, Germany.
-
C.
Sausheim
Sausheim is a commune in the Haut-Rhin department of the Grand Est region in northeastern France, situated near the city of Mulhouse.
-
D.
Sulzheim
Sulzheim is a small municipality in the Schweinfurt district of Lower Franconia in northern Bavaria, Germany.
-
E.
Dossenheim
Dossenheim is a municipality in southwestern Germany near Heidelberg, known for its agricultural research facilities and scenic location along the Bergstraße.
- 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_69e11e5010e48190ae1e9c9db9697637 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15adda0e48190825a5b705ae52d5b |
completed | April 29, 2026, 1:11 a.m. |
Created at: April 16, 2026, 8:47 p.m.