Triple
T8371210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erbach (Donau) |
E197457
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Erbach, Hesse |
E345881
|
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: Erbach, Hesse | Statement: [Erbach (Donau), hasTwinTown, Erbach, Hesse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erbach, Hesse Context triple: [Erbach (Donau), hasTwinTown, Erbach, Hesse]
-
A.
Erbach, Hesse
chosen
Erbach, Hesse is a small town in southwestern Germany known for its historic castle, ivory carving tradition, and picturesque location in the Odenwald region.
-
B.
Eberbach
Eberbach is a small historic town in southwestern Germany, known for its picturesque location in the Odenwald hills along the Neckar River.
-
C.
Frankenberg, Hesse
Frankenberg, Hesse is a small historic town in the German state of Hesse, known for its medieval architecture and location in the Eder river valley.
-
D.
Hesse-Braubach
Hesse-Braubach was a minor cadet line of the German princely House of Hesse-Darmstadt, centered around the town of Braubach.
-
E.
Schambach
Schambach is a small river in Bavaria, Germany, that flows into the Altmühl as one of its tributaries.
- 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_69ca82f56730819080cec5d991c76f4c |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80a509dc81909e0ea4c66b21d84f |
completed | March 31, 2026, 8:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc79752b48190933ea644a59f2305 |
completed | April 2, 2026, 1:34 a.m. |
Created at: March 30, 2026, 6:01 p.m.