Triple
T9766451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konstanz |
E237005
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Bodensee |
E176598
|
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: Bodensee | Statement: [Konstanz, locatedOn, Bodensee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bodensee Context triple: [Konstanz, locatedOn, Bodensee]
-
A.
Schönenbodensee
Schönenbodensee is a small scenic mountain lake located near the village of Wildhaus in the Toggenburg region of the Swiss canton of St. Gallen.
-
B.
Lake Constance
chosen
Lake Constance is a large freshwater lake on the Rhine at the northern foot of the Alps, bordering Germany, Austria, and Switzerland and serving as a major regional hub for tourism, transport, and natural conservation.
-
C.
Jungfernsee
Jungfernsee is a scenic lake on the outskirts of Potsdam and Berlin, known for its historic villas, palaces, and location along the former inner German border.
-
D.
Tüttensee
Tüttensee is a small lake in the Chiemgau region of Bavaria, Germany, known for its scenic setting and local recreational use.
-
E.
Chiemsee
Chiemsee is one of Germany’s largest lakes, famed for its scenic Alpine setting and historic islands such as Herrenchiemsee with its royal palace.
- 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_69ca84d831b8819090322686b47887ce |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda0a15e408190909745cb1c30937d |
completed | April 1, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dbd9073c948190aa2e9e6b7ffe9022 |
completed | April 12, 2026, 5:40 p.m. |
Created at: March 30, 2026, 8:25 p.m.