Triple
T30817627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belgian transport infrastructure |
E784826
|
entity |
| Predicate | railNetworkLengthKm |
P121115
|
FINISHED |
| Object | approximately 3600 |
—
|
LITERAL 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: approximately 3600 | Statement: [Belgian transport infrastructure, railNetworkLengthKm, approximately 3600]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railNetworkLengthKm Context triple: [Belgian transport infrastructure, railNetworkLengthKm, approximately 3600]
-
A.
railwayNetworkLength
chosen
Indicates the total measured length of all railway tracks within a specified railway network.
-
B.
railwayLineLength
Indicates the total measured length of a railway line.
-
C.
railroadNetwork
Indicates a relationship where locations are connected as part of the same system of railway lines and infrastructure used for train transport.
-
D.
numberOfRailLines
Indicates the total count of rail lines associated with or serving a given entity.
-
E.
numberOfElectrifiedLines
Indicates the quantity of railway or transit lines within a system or network that are equipped with electrical power infrastructure for operation.
- F. None of above.
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_69f224b4eda48190bd212ce4f3901e56 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6906994e88190a2da183455bdf076 |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b7d2794819092fef8a63f4f3de8 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:44 p.m.