Triple
T4747021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bundesplatz |
E105383
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Käfigturm |
E99405
|
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: Käfigturm | Statement: [Bundesplatz, near, Käfigturm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Käfigturm Context triple: [Bundesplatz, near, Käfigturm]
-
A.
Käfigturm
chosen
Käfigturm is a historic medieval tower and former city gate in Bern, Switzerland, now serving as a prominent landmark and cultural venue.
-
B.
Schmalzturm
Schmalzturm is a historic medieval tower and notable architectural landmark in the Bavarian town of Weißenburg in Bayern, Germany.
-
C.
Schmalzturm
Schmalzturm is a historic medieval tower in the Bavarian town of Landsberg am Lech, notable as a landmark of its old town fortifications.
-
D.
Roter Turm
Roter Turm is a historic clock and bell tower in Halle (Saale), Germany, and one of the city’s most recognizable architectural landmarks.
-
E.
Roter Turm
Roter Turm is a historic medieval tower and prominent architectural landmark in the city center of Chemnitz, 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_69bd43f07fa48190954317d01600994a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64c3fcb081909b1fe867b4adac8b |
completed | March 20, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be3a46fd608190a81b13d0f687d4ed |
completed | March 21, 2026, 6:27 a.m. |
Created at: March 20, 2026, 1:20 p.m.