Triple
T22038688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Elisabeth Cathedral |
E544280
|
entity |
| Predicate | nearby |
P350
|
FINISHED |
| Object | Urban Tower |
—
|
NE NERFINISHED |
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: Urban Tower | Statement: [St Elisabeth Cathedral, nearby, Urban Tower]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Urban Tower Context triple: [St Elisabeth Cathedral, nearby, Urban Tower]
-
A.
Urban Tower
chosen
Urban Tower is a historic Gothic bell tower and prominent architectural landmark located in the center of Košice, Slovakia.
-
B.
Incity Tower
Incity Tower is a prominent modern skyscraper in Lyon, France, known for its distinctive design and role in the city’s business district skyline.
-
C.
city towers
City towers are prominent historic defensive and watchtower structures that characterize the skyline and medieval fortifications of Isny im Allgäu.
-
D.
City Tower
City Tower is a prominent residential skyscraper in Downtown Brooklyn known for its modern high-rise apartments and amenities.
-
E.
Metro Tower
Metro Tower is a prominent landmark skyscraper in Metro City, recognized as one of its most notable architectural features.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e2f98c8819083e11eab90942a78 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127f42b48819095b04bad34e0e3c4 |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:25 p.m.