Triple
T2671710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brussels Metro |
E55760
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Heysel – Heizel |
E235402
|
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: Heysel – Heizel | Statement: [Brussels Metro, hasStation, Heysel – Heizel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heysel – Heizel Context triple: [Brussels Metro, hasStation, Heysel – Heizel]
-
A.
Heysel Plateau
chosen
The Heysel Plateau is a prominent area in northern Brussels known for hosting major exhibition halls, the Atomium landmark, and various cultural and recreational facilities.
-
B.
Holthees
Holthees is a small village in the Dutch province of North Brabant, known for its rural character and historic church.
-
C.
Heidkrüger
Heidkrüger is the original German surname of actress and former fashion model Diane Kruger.
-
D.
Löhr
Löhr is a German-language surname borne by various notable individuals, including figures in military, arts, and public life.
-
E.
Haldenstein
Haldenstein is a small Swiss village in the canton of Graubünden, known in architecture circles as the longtime base of renowned architect Peter Zumthor.
- 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_69ab49e54de48190be708cd1cf8be073 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd98f98908190b5c6fb38d3d4367a |
completed | March 7, 2026, 7:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afa05f1ba48190a93a399d1067912c |
completed | March 10, 2026, 4:38 a.m. |
Created at: March 6, 2026, 9:54 p.m.