Triple
T17761870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Opernplatz |
E443396
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Lucae-Brunnen |
—
|
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: Lucae-Brunnen | Statement: [Opernplatz, hasLandmark, Lucae-Brunnen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lucae-Brunnen Context triple: [Opernplatz, hasLandmark, Lucae-Brunnen]
-
A.
Brunnen
Brunnen is a Swiss lakeside village on Lake Lucerne in the canton of Schwyz, known for its scenic alpine setting and role as a popular tourist destination.
-
B.
Mendebrunnen fountain
chosen
The Mendebrunnen fountain is a historic neo-baroque fountain in Leipzig, Germany, known as one of the city’s most prominent and ornate public monuments.
-
C.
Neptunbrunnen
Neptunbrunnen is a historic fountain in central Berlin featuring a monumental statue of Neptune surrounded by allegorical figures representing major German rivers.
-
D.
Roman Well
Roman Well is a historic underground water reservoir and tourist attraction located within Belgrade Fortress in Belgrade, Serbia.
-
E.
Schängelbrunnen
Schängelbrunnen is a famous bronze fountain in Koblenz, Germany, depicting a mischievous boy and symbolizing the city's local identity and dialect.
- 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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e485f887ac81908c896a50175692b9 |
completed | April 19, 2026, 7:36 a.m. |
Created at: April 10, 2026, 10:11 a.m.