Triple
T8225975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 Brussels bombings |
E192172
|
entity |
| Predicate | metroStation |
P28508
|
FINISHED |
| Object | Maelbeek |
E187509
|
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: Maelbeek | Statement: [2016 Brussels bombings, metroStation, Maelbeek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maelbeek Context triple: [2016 Brussels bombings, metroStation, Maelbeek]
-
A.
De Brouckère
De Brouckère is a major Brussels Metro station and transport hub located in the central part of Brussels, Belgium.
-
B.
Maelbeek metro station
chosen
Maelbeek metro station is a Brussels Metro station in Belgium’s European Quarter, known for serving key EU institutions and for being one of the sites of the 2016 Brussels bombings.
-
C.
Koekelberg
Koekelberg is a small municipality in the Brussels-Capital Region of Belgium, known for the National Basilica of the Sacred Heart that dominates its skyline.
-
D.
Meise
Meise is a municipality in the Belgian province of Flemish Brabant, known for hosting the National Botanic Garden of Belgium.
-
E.
Manneken Pis
Manneken Pis is a small bronze statue and fountain of a urinating boy in Brussels, serving as one of the city’s most iconic and humorous landmarks.
- 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_69ca82c9a8ac81908b011c38698456e4 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb77fc10f48190b7e241c89885a478 |
completed | March 31, 2026, 7:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccee0fd9d0819094350c9c7887cabe |
completed | April 1, 2026, 10:06 a.m. |
Created at: March 30, 2026, 5:45 p.m.