Triple
T23310555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GVB Amsterdam |
E590569
|
entity |
| Predicate | customerServiceLanguage |
P112988
|
FINISHED |
| Object | Dutch |
—
|
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: Dutch | Statement: [GVB Amsterdam, customerServiceLanguage, Dutch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: customerServiceLanguage Context triple: [GVB Amsterdam, customerServiceLanguage, Dutch]
-
A.
hasCustomerServiceLanguage
chosen
Indicates that an entity provides customer service in a specified language or set of languages.
-
B.
serviceBrandLanguage
Indicates the language or languages in which a service brand communicates or is presented.
-
C.
currentLanguageOfServices
Indicates that a specified language is the one presently used to provide or deliver certain services.
-
D.
serviceBranchLanguage
Indicates the language or languages used or officially recognized by a particular branch of a service (such as a military or organizational branch).
-
E.
requiredLanguage
Indicates that a specific language is necessary or must be used for a given entity, action, or interaction.
- 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1972acad08190bb56541b822555cd |
completed | April 29, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:05 p.m.