Triple
T20516675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dom zu Unserer Lieben Frau |
E503698
|
entity |
| Predicate | cityPanoramaRule |
P4219
|
FINISHED |
| Object | traditionally tallest building in central Munich |
—
|
LITERAL 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: traditionally tallest building in central Munich | Statement: [Dom zu Unserer Lieben Frau, cityPanoramaRule, traditionally tallest building in central Munich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityPanoramaRule Context triple: [Dom zu Unserer Lieben Frau, cityPanoramaRule, traditionally tallest building in central Munich]
-
A.
cityPanorama
chosen
Indicates a wide, comprehensive visual view or representation of a cityscape, typically encompassing many of its features in a single scene.
-
B.
cityView
Indicates that one entity offers a view of, or overlooks, a city.
-
C.
urbanLayout
Indicates how the spatial arrangement, organization, and structure of buildings, streets, and public spaces relate to one another within an urban area.
-
D.
cityScene
Indicates a scene or setting that takes place within an urban or city environment.
-
E.
cityOverlooks
Indicates that a city has a direct visual view over or across a particular geographic feature, area, or landmark.
- F. None of above.
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_69e0b4b2aa788190ae9eb37c1d73b1f1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69f42db688190a3ccfba5601e8bf3 |
completed | April 20, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69e59fdb7ad88190924176c32a195db3 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:36 a.m.