Triple
T15670472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Brieuc |
E377295
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Alsdorf |
E845345
|
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: Alsdorf | Statement: [Saint-Brieuc, twinTown, Alsdorf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alsdorf Context triple: [Saint-Brieuc, twinTown, Alsdorf]
-
A.
Alsdorf
chosen
Alsdorf is a town in western Germany’s North Rhine-Westphalia, historically shaped by coal mining and now part of the Aachen city region.
-
B.
Tasdorf
Tasdorf is a small municipality in northern Germany notable as the birthplace of the 19th-century opera composer Giacomo Meyerbeer.
-
C.
Aulendorf
Aulendorf is a small town in the Upper Swabia region of southern Germany, known for its historic castle and spa facilities.
-
D.
Sierksdorf
Sierksdorf is a small coastal municipality in northern Germany, known for its Baltic Sea beaches and the Hansa-Park amusement park.
-
E.
Porschdorf
Porschdorf is a village in Saxony, Germany, that forms part of the spa town and municipality of Bad Schandau in the Saxon Switzerland region.
- 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f1254508190a77a16b7bfd299ad |
completed | April 16, 2026, 2:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb59535908190a3d085a5e74b06e8 |
completed | May 9, 2026, 10:30 p.m. |
Created at: April 10, 2026, 4:16 a.m.