Triple
T17858209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hesselberg |
E445995
|
entity |
| Predicate | nearestTown |
P350
|
FINISHED |
| Object | Ehingen |
—
|
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: Ehingen | Statement: [Hesselberg, nearestTown, Ehingen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ehingen Context triple: [Hesselberg, nearestTown, Ehingen]
-
A.
Ehingen
Ehingen is a town in the state of Baden-Württemberg in southern Germany, known for its historic center and location along the Danube River.
-
B.
Ehingen am Ries
chosen
Ehingen am Ries is a small rural municipality in the Donau-Ries district of Bavaria in southern Germany, known for its location in the geologically distinctive Nördlinger Ries crater region.
-
C.
Ehningen
Ehningen is a small German municipality in the state of Baden-Württemberg, located near Stuttgart and known for its mix of residential areas and technology-oriented businesses.
-
D.
Eppenhain
Eppenhain is a district of the town of Kelkheim in the Main-Taunus region of Hesse, Germany, known for its proximity to the Taunus hills and forested surroundings.
-
E.
Ehringshausen
Ehringshausen is a municipality in the Lahn-Dill district of the German state of Hesse.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4978e68ec8190a4306f7b7bb058d7 |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.