Triple
T2646783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dom Square |
E53802
|
entity |
| Predicate | hasViewOf |
P854
|
FINISHED |
| Object | Dom Tower |
E285137
|
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: Dom Tower | Statement: [Dom Square, hasViewOf, Dom Tower]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dom Tower Context triple: [Dom Square, hasViewOf, Dom Tower]
-
A.
Dom Tower
chosen
Dom Tower is the iconic medieval church tower of Utrecht in the Netherlands, renowned as the country’s tallest and a prominent symbol of the city.
-
B.
Terminal Tower
Terminal Tower is a historic skyscraper in downtown Cleveland, Ohio, that long served as a major office building and transportation hub and was once one of the tallest buildings in the world.
-
C.
Leland Tower
Leland Tower is a historic high-rise building in downtown Aurora, Illinois, once the tallest building in the state outside Chicago and a prominent local landmark.
-
D.
Hilton Tower
Hilton Tower is the common name for Beetham Tower, a prominent mixed-use skyscraper and landmark on Manchester’s skyline.
-
E.
Marathon Tower
Marathon Tower was a prominent architectural feature of the 1928 Amsterdam Olympic Stadium, serving as a symbolic focal point for the Games and the marathon event.
- 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_69ab495e192081909c77b622e8e7e15a |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd919bf2c81908feb768f3391e985 |
completed | March 7, 2026, 7:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afa050cc408190b2fa81a0f2da06eb |
completed | March 10, 2026, 4:38 a.m. |
Created at: March 6, 2026, 9:53 p.m.