Triple
T12132244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line 5 (Brussels Metro) |
E288960
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Schuman station |
E187510
|
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: Schuman station | Statement: [Line 5 (Brussels Metro), hasStation, Schuman station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schuman station Context triple: [Line 5 (Brussels Metro), hasStation, Schuman station]
-
A.
Schuman metro station
chosen
Schuman metro station is a key public transport hub in Brussels, serving metro and rail lines that connect the European Union institutions with the rest of the city and region.
-
B.
Jacques Brel station
Jacques Brel station is a Brussels Metro station named after the famed Belgian singer-songwriter Jacques Brel.
-
C.
Viarmes station
Viarmes station is a railway stop in the commune of Viarmes in northern France, serving local passenger trains on the regional network.
-
D.
Mabillon station
Mabillon station is a Paris Métro station in the 6th arrondissement, serving the Saint-Germain-des-Prés area on the Left Bank.
-
E.
Maadi station
Maadi station is a Cairo Metro station serving the Maadi district in southern Cairo, Egypt.
- 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_69d6ab4b5e4c81909950b17151eb0951 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9158b34648190b5eecdf9b07fbb3f |
completed | April 10, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63458b22c8190b2a7d4a9cd25dfe1 |
completed | May 2, 2026, 5:28 p.m. |
Created at: April 8, 2026, 9:49 p.m.