Triple
T35345427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Brabant rail network |
E1020726
|
entity |
| Predicate | hasMainOperator |
P95216
|
FINISHED |
| Object | Nederlandse Spoorwegen |
E28405
|
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: Nederlandse Spoorwegen | Statement: [North Brabant rail network, hasMainOperator, Nederlandse Spoorwegen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainOperator Context triple: [North Brabant rail network, hasMainOperator, Nederlandse Spoorwegen]
-
A.
hasMainOperatorFlagState
Indicates that an entity’s primary operator is associated with, or currently in, a specific flag-defined state.
-
B.
hasMajorOperator
chosen
Indicates that an entity is primarily operated, managed, or run by a specified main operator or organization.
-
C.
hasMainOperations
Indicates that an entity is associated with its primary or core operations, activities, or functions.
-
D.
hasAdditionalOperator
Indicates that an entity is associated with one or more supplementary operators beyond its primary or default operator.
-
E.
hasComplementaryOperator
Indicates that one operator is associated with another operator that performs a complementary or inverse function to it.
- F. None of above.
Provenance (4 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_69f76decd95c8190ae428f6a19d535de |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a021f84715881908e25b6548e7cf62e |
completed | May 11, 2026, 6:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3823d02c1c8190b96473ed3600bd93 |
completed | June 21, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_6a021739b7288190a4ca94c04074c78a |
completed | May 11, 2026, 5:51 p.m. |
Created at: May 3, 2026, 4:03 p.m.