Triple
T9146313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Starnberg |
E219462
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Roseninsel |
E231627
|
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: Roseninsel | Statement: [Lake Starnberg, hasIsland, Roseninsel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roseninsel Context triple: [Lake Starnberg, hasIsland, Roseninsel]
-
A.
Roseninsel
chosen
Roseninsel is a small, historically significant island in Lake Starnberg in Bavaria, Germany, known for its rose gardens and former royal retreat.
-
B.
Rote Insel
Rote Insel is a distinctive, historically working-class neighborhood in Berlin known for its island-like layout encircled by railway lines and its rich social and cultural history.
-
C.
Sasseninsel
Sasseninsel is a small island located in the Eibsee, a picturesque alpine lake near the Zugspitze in Bavaria, Germany.
-
D.
Humboldt-Insel
Humboldt-Insel is a small island in Berlin’s Spree River, known for its residential areas and proximity to the city’s central districts.
-
E.
Johannisinsel
Johannisinsel is a small island in the Königssee lake in Bavaria, Germany, known for its historic statue of Saint John of Nepomuk.
- 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_69ca83e121dc81909912bd66953081c5 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca917914c8190b97ca9169bbd1e5e |
completed | April 1, 2026, 5:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09b75186c8190849f86b7e26093f1 |
completed | April 4, 2026, 5:02 a.m. |
Created at: March 30, 2026, 7:20 p.m.