Triple
T15531915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Großgörschenstraße |
E370239
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Schöneberg |
E13289
|
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: Schöneberg | Statement: [Großgörschenstraße, locatedIn, Schöneberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schöneberg Context triple: [Großgörschenstraße, locatedIn, Schöneberg]
-
A.
Schöneberg
chosen
Schöneberg is a district of Berlin, Germany, historically notable as the site of John F. Kennedy’s famous “Ich bin ein Berliner” speech.
-
B.
Schönewalde
Schönewalde is a town in the state of Brandenburg, Germany, known for hosting a German Air Force base.
-
C.
Schönholz
Schönholz is a locality in Berlin, Germany, served by the city’s S-Bahn rapid transit network.
-
D.
Petershagen
Petershagen is a small town in North Rhine-Westphalia, Germany, known for its historic architecture and scenic location along the Weser River.
-
E.
Schönwalde
Schönwalde is a locality within the municipality of Wandlitz in the state of Brandenburg, Germany.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e0414877d88190804ee76566004e13 |
completed | April 16, 2026, 1:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f2d4b1c81909ff876289db20803 |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:06 a.m.