Triple
T20884680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Törten Housing Estate |
E514244
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Törten |
—
|
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: Törten | Statement: [Törten Housing Estate, namedAfter, Törten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Törten Context triple: [Törten Housing Estate, namedAfter, Törten]
-
A.
Törten
chosen
Törten is a district of Dessau, Germany, best known for its Bauhaus-era experimental housing estate designed by Walter Gropius.
-
B.
Tortenstück
Tortenstück is the popular nickname for Frankfurt’s Museum für Moderne Kunst, known for its distinctive triangular, cake-slice-shaped architecture.
-
C.
Punschkrapfen
Punschkrapfen is a traditional Austrian pastry consisting of rum-soaked sponge cake coated in pink fondant, often associated with classic Viennese coffeehouse culture.
-
D.
Lokma
Lokma is a traditional Turkish dessert consisting of small deep-fried dough balls soaked in syrup, often served at celebrations and communal events.
-
E.
Strudel
Strudel is a traditional Central European pastry made from thinly rolled dough filled with sweet or savory ingredients, most famously apple.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67bd32c819097301e330e358c49 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.