Triple
T10670971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankfurt skyline |
E251483
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Main Tower |
E93339
|
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: Main Tower | Statement: [Frankfurt skyline, hasPart, Main Tower]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Main Tower Context triple: [Frankfurt skyline, hasPart, Main Tower]
-
A.
Main Tower
chosen
Main Tower is a prominent modern skyscraper in Frankfurt am Main, Germany, known for its public observation deck offering panoramic views of the city.
-
B.
West Tower
West Tower is the prominent western bell and clock tower of Ely Cathedral, notable for its imposing Gothic architecture and role as a key landmark of the historic church.
-
C.
West Tower
West Tower is a prominent residential skyscraper within the Deansgate Square complex in Manchester, England.
-
D.
Wood Tower
Wood Tower is a historic medieval watchtower and former city gate located in the German city of Mainz along the Rhine River.
-
E.
Aspect Tower
Aspect Tower is one of the residential skyscrapers within the Executive Towers complex in Dubai’s Business Bay district.
- 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_69d6aa5b0d2881909584b20efc5877f0 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6f86390648190851693aedce6b7ad |
completed | April 9, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98865f700819093c8cadc6fcef75f |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:09 p.m.