Triple
T21096901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Newport |
E519790
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Heidenheim an der Brenz |
—
|
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: Heidenheim an der Brenz | Statement: [Newport, hasTwinTown, Heidenheim an der Brenz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heidenheim an der Brenz Context triple: [Newport, hasTwinTown, Heidenheim an der Brenz]
-
A.
Heidenheim an der Brenz
chosen
Heidenheim an der Brenz is a town in the German state of Baden-Württemberg known for its industrial heritage, historic castle Hellenstein, and location on the Brenz River near the Swabian Jura.
-
B.
Nenzing
Nenzing is a small market town in the Austrian state of Vorarlberg, near the border with Liechtenstein and Switzerland.
-
C.
Heidenau
Heidenau is a small town in the German state of Saxony, located near Dresden along the Elbe River.
-
D.
Oberteuringen
Oberteuringen is a municipality in the Bodenseekreis district of the German state of Baden-Württemberg, located near Lake Constance.
-
E.
Biberach an der Riß
Biberach an der Riß is a historic town in the German state of Baden-Württemberg, known for its well-preserved medieval old town and traditional Swabian culture.
- 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_69e0b508d8dc81909be940dafe36c8f7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e71b595cdc8190ba7a6f3f71d40c3f |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 2:52 p.m.