Triple
T8601685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brussels–Amsterdam |
E203690
|
entity |
| Predicate | usesInfrastructure |
P6820
|
FINISHED |
| Object | HSL 4 |
E389232
|
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: HSL 4 | Statement: [Brussels–Amsterdam, usesInfrastructure, HSL 4]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HSL 4 Context triple: [Brussels–Amsterdam, usesInfrastructure, HSL 4]
-
A.
HSL 4
chosen
HSL 4 is a Belgian high-speed railway line that connects Antwerp to the Dutch border as part of the international high-speed rail corridor between Brussels and Amsterdam.
-
B.
HSL 3
HSL 3 is a Belgian high-speed railway line that connects Liège to the German border as part of the international high-speed rail corridor between Brussels and Germany.
-
C.
HSL 2
HSL 2 is a Belgian high-speed railway line primarily used for fast passenger services between major cities and international connections.
-
D.
HSL 1
HSL 1 is a Belgian high-speed railway line that forms part of the international route used by Eurostar and other high-speed services between Brussels and neighboring countries.
-
E.
HSL
HSL is the three-letter National Rail station code for Haslemere railway station in Surrey, England.
- 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_69ca832b56948190ba751cec255308f1 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46da609881909a6d851915e8df14 |
completed | March 31, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea8f13f7081908317c1b2d87a51b2 |
completed | April 2, 2026, 5:35 p.m. |
Created at: March 30, 2026, 6:24 p.m.