Triple
T3162442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Market Drayton |
E66130
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Arlon |
E154217
|
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: Arlon | Statement: [Market Drayton, hasTwinTown, Arlon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arlon Context triple: [Market Drayton, hasTwinTown, Arlon]
-
A.
Arlon
chosen
Arlon is a historic town in southeastern Belgium that serves as the capital of the province of Luxembourg in the Walloon Region.
-
B.
Porrentruy
Porrentruy is a historic town in northwestern Switzerland known for its medieval castle and role as a regional center in the canton of Jura.
-
C.
Bossey
Bossey is a small French commune in the Haute-Savoie department of the Auvergne-Rhône-Alpes region, located near the Swiss border south of Geneva.
-
D.
Murten
Murten is a historic bilingual town in the canton of Fribourg, Switzerland, known for its well-preserved medieval old town and lakeside setting on Lake Murten.
-
E.
Rixensart
Rixensart is a municipality in Walloon Brabant, Belgium, known for its residential character and proximity to Brussels.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada618b9b88190afaa6d47dcad9f2c |
completed | March 8, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e81e6f98819099317f97f0c7f546 |
completed | March 12, 2026, 4:21 p.m. |
Created at: March 8, 2026, 3:06 p.m.