Triple
T16158268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graben |
E392108
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Kohlmarkt |
E346718
|
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: Kohlmarkt | Statement: [Graben, connectsTo, Kohlmarkt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kohlmarkt Context triple: [Graben, connectsTo, Kohlmarkt]
-
A.
Kohlmarkt
chosen
Kohlmarkt is a historic and upscale shopping street in Vienna’s city center, known for its luxury boutiques and elegant architecture.
-
B.
Oude Markt
Oude Markt is a historic central square in Leuven, Belgium, famed for its dense concentration of cafés and bars and often nicknamed “the longest bar in the world.”
-
C.
St. Johanner Markt
St. Johanner Markt is a historic central square in Saarbrücken known for its baroque architecture, lively cafés, and role as a popular social and cultural gathering place.
-
D.
Rathausmarkt
Rathausmarkt is the large central square in Hamburg that serves as the main public plaza in front of the city hall and a key venue for events, markets, and civic gatherings.
-
E.
Rochusmarkt
Rochusmarkt is a traditional open-air market in Vienna known for its fresh produce, food stalls, and neighborhood atmosphere.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21e5c9cd0819090e34ee163ffb118 |
completed | April 17, 2026, 11:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff7b05a588190a44d1c922195a87b |
completed | May 10, 2026, 3:12 a.m. |
Created at: April 10, 2026, 5:01 a.m.