Triple
T20366131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Falmouth |
E496912
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Rotenburg (Wümme) |
—
|
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: Rotenburg (Wümme) | Statement: [Falmouth, hasTwinTown, Rotenburg (Wümme)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rotenburg (Wümme) Context triple: [Falmouth, hasTwinTown, Rotenburg (Wümme)]
-
A.
Rotenburg (Wümme)
chosen
Rotenburg (Wümme) is a small town in Lower Saxony, Germany, known for its rural surroundings and role as a local administrative and service center.
-
B.
Lehrte
Lehrte is a town in Lower Saxony, Germany, located east of Hanover and known historically for its railway junction and agricultural surroundings.
-
C.
Northeim
Northeim is a town in Lower Saxony, Germany, known for its medieval old town and location in the Leine River valley.
-
D.
Rotenburg an der Fulda
Rotenburg an der Fulda is a historic small town in northeastern Hesse, Germany, situated along the Fulda River and known for its well-preserved half-timbered architecture.
-
E.
Weickede
Weickede is a village-level subdivision of the town of Rüthen in the district of Soest, North Rhine-Westphalia, Germany.
- 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_69e0b4a4f9b081908a5a021919c21ccb |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67871bfdc8190948c46497cd675c9 |
completed | April 20, 2026, 7:03 p.m. |
Created at: April 16, 2026, 11:26 a.m.