Triple
T15586852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bundeshaus |
E374643
|
entity |
| Predicate | hasPlaza |
P13926
|
FINISHED |
| Object | Bundesplatz |
E105383
|
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: Bundesplatz | Statement: [Bundeshaus, hasPlaza, Bundesplatz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bundesplatz Context triple: [Bundeshaus, hasPlaza, Bundesplatz]
-
A.
Bundesplatz
Bundesplatz is a public square and transport hub in Berlin that serves as an important interchange point for city and suburban rail services.
-
B.
Bundesplatz
chosen
Bundesplatz is the central public square in Bern, Switzerland, located in front of the Federal Palace and often used for political events, markets, and public gatherings.
-
C.
Europaplatz
Europaplatz is a public square in Munich, Germany, known as a local transport and urban hub within the city.
-
D.
Schlossplatz
Schlossplatz is a historic central square in Berlin that once fronted the Berlin City Palace and now serves as the site of the reconstructed Humboldt Forum.
-
E.
Schlossplatz
Schlossplatz is the central historic square of Wiesbaden, Germany, surrounded by notable buildings such as the city palace and town hall and serving as a key venue for public events.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e4900408190aadb48b001db4169 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00456b590c8190949fd23cb5cec1e8 |
completed | May 10, 2026, 8:44 a.m. |
Created at: April 10, 2026, 4:11 a.m.