Triple
T15937058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donaustadt |
E386464
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | UNO City |
E386465
|
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: UNO City | Statement: [Donaustadt, hasLandmark, UNO City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UNO City Context triple: [Donaustadt, hasLandmark, UNO City]
-
A.
UNO City
chosen
UNO City is a major United Nations complex in Vienna that hosts several UN organizations and international agencies.
-
B.
Canon City
Canon City is a small city in central Colorado known for its historic downtown, proximity to the Royal Gorge, and outdoor recreation along the Arkansas River.
-
C.
Ciudad del Río
Ciudad del Río is a revitalized urban district in Medellín, Colombia, known for its contemporary architecture, public green spaces, and cultural attractions.
-
D.
Plaza City
Plaza City is a nickname for Orange, California, highlighting its historic central plaza and small-town, old-fashioned downtown charm.
-
E.
Square City
Square City is a walled, square-shaped fortress-like structure that serves as the main gate complex and defensive enclosure at the entrance to the Ming Xiaoling Mausoleum in Nanjing, China.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156ab7f548190b2d1aafa0e6d2c24 |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb5b8121881909b15bf6451d3d3a8 |
completed | May 9, 2026, 10:31 p.m. |
Created at: April 10, 2026, 4:53 a.m.