Triple
T3464555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westphalweg |
E73104
|
entity |
| Predicate | servedByDirection |
P48943
|
FINISHED |
| Object | Alt-Mariendorf |
E79213
|
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: Alt-Mariendorf | Statement: [Westphalweg, servedByDirection, Alt-Mariendorf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alt-Mariendorf Context triple: [Westphalweg, servedByDirection, Alt-Mariendorf]
-
A.
Alt-Mariendorf
chosen
Alt-Mariendorf is a Berlin U-Bahn station in the Mariendorf district that serves as the southern terminus of line U6.
-
B.
Friedrichsdorf
Friedrichsdorf is a town in the German state of Hesse, located north of Frankfurt and known historically for its Huguenot heritage and proximity to the Taunus mountains.
-
C.
Lichterfelde
Lichterfelde is a residential district in southwestern Berlin known for its historic villas, leafy streets, and affluent character.
-
D.
Langendorf
Langendorf is a municipality in the canton of Solothurn in northwestern Switzerland.
-
E.
Lippendorf
Lippendorf is a village in Saxony, Germany, historically notable as the birthplace of Katharina von Bora, the wife of Martin Luther.
- 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_69ad85b224d481908ff8be51338d24ff |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb0dc100819084bb0c355c7bb15b |
completed | March 8, 2026, 6:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b373aaff688190b9f12a7042055a1c |
completed | March 13, 2026, 2:17 a.m. |
Created at: March 8, 2026, 3:17 p.m.