Triple
T4998768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metro line 50 |
E112313
|
entity |
| Predicate | routeCharacteristic |
P8860
|
FINISHED |
| Object | does not pass through Amsterdam Centraal |
—
|
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: does not pass through Amsterdam Centraal | Statement: [Metro line 50, routeCharacteristic, does not pass through Amsterdam Centraal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routeCharacteristic Context triple: [Metro line 50, routeCharacteristic, does not pass through Amsterdam Centraal]
-
A.
routeNetworkCharacteristic
chosen
Indicates a relationship where a specific characteristic or property is attributed to a route within a network.
-
B.
roadFeature
Indicates that an entity is a specific physical or functional characteristic associated with a road, such as its structure, markings, or related infrastructure.
-
C.
roadTraverses
Indicates that a road passes through, crosses, or extends across a specified geographic area or feature.
-
D.
routeBetween
Indicates that there exists a path or connection enabling travel or communication between two locations or points.
-
E.
roadType
Indicates the classification or category of a road based on its functional or physical characteristics.
- 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7472a1dc8190942f568a81fdd961 |
completed | March 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69bd714aee2481908fb0dd5fa2daf3a1 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:34 p.m.