Triple
T12894478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Die tote Stadt |
E308455
|
entity |
| Predicate | cityAsSymbol |
P107318
|
FINISHED |
| Object | Bruges as a "dead" city of memory |
—
|
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: Bruges as a "dead" city of memory | Statement: [Die tote Stadt, cityAsSymbol, Bruges as a "dead" city of memory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityAsSymbol Context triple: [Die tote Stadt, cityAsSymbol, Bruges as a "dead" city of memory]
-
A.
citySymbol
Indicates that one entity serves as the official symbol or emblem representing a particular city.
-
B.
citySymbolOf
Indicates that a particular city serves as an official symbol or emblem representing another entity, such as a region, organization, or concept.
-
C.
citySymbolStatus
Indicates the status or condition of a symbol associated with a city, such as whether it is official, active, or recognized.
-
D.
cityRepresentation
Indicates that one entity serves as the official or primary representative (such as a government, organization, or office) for a particular city in some context.
-
E.
cantonSymbol
Indicates that one entity serves as the official symbol or emblem representing a particular canton.
- F. None of above. chosen
Provenance (4 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971484aa08190a8adfafabe600903 |
completed | April 10, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69d96fa776648190b9b5c30722ea50b6 |
completed | April 10, 2026, 9:46 p.m. |
| PDg | Predicate description generation | batch_69d9713e45a88190acd346f066093550 |
completed | April 10, 2026, 9:53 p.m. |
Created at: April 9, 2026, 5:40 p.m.