Triple
T16209818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grande Île de Strasbourg |
E393432
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Maison Kammerzell |
E85723
|
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: Maison Kammerzell | Statement: [Grande Île de Strasbourg, contains, Maison Kammerzell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maison Kammerzell Context triple: [Grande Île de Strasbourg, contains, Maison Kammerzell]
-
A.
Maison Kammerzell
chosen
Maison Kammerzell is a richly ornamented late Gothic and Renaissance timber-framed house in Strasbourg, France, renowned as one of the city’s most iconic historic buildings.
-
B.
Almenhof
Almenhof is a residential district of Mannheim in the German state of Baden-Württemberg.
-
C.
Damböckhaus
Damböckhaus is a mountain hut located on the slopes of the Schneeberg in Lower Austria, serving as a popular rest stop for hikers and mountaineers.
-
D.
Marienhof
Marienhof is a German television soap opera that gained popularity in the 1990s and 2000s for its portrayal of everyday life and relationships in a fictional Cologne neighborhood.
-
E.
Haus Salzhaus
Haus Salzhaus is a historic building on Frankfurt’s Römerberg square, known for its richly decorated Renaissance-style façade and role in the city’s old town ensemble.
- 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_69d87f1f5bd08190bd01cac0d5b9d2ef |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e22711e4fc8190bf7a9f0c59b7889f |
completed | April 17, 2026, 12:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0007916d3481909d475f1661d80e77 |
completed | May 10, 2026, 4:20 a.m. |
Created at: April 10, 2026, 5:03 a.m.