Triple
T14145548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lignes d’Azur |
E350538
|
entity |
| Predicate | hasCustomerServiceLanguage |
P112988
|
FINISHED |
| Object | French |
—
|
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: French | Statement: [Lignes d’Azur, hasCustomerServiceLanguage, French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCustomerServiceLanguage Context triple: [Lignes d’Azur, hasCustomerServiceLanguage, French]
-
A.
hasCustomerServices
Indicates that an entity provides or is associated with one or more customer service functions or offerings.
-
B.
hasLanguageOfOrders
Indicates that one entity uses or is associated with a particular language for issuing orders or commands to another entity.
-
C.
serviceBrandLanguage
Indicates the language or languages in which a service brand communicates or is presented.
-
D.
hasCustomerServiceChannel
Indicates that an entity provides or is associated with a specific channel or medium through which customer service interactions can occur.
-
E.
hasTargetAudienceLanguage
Indicates that something is intended for or directed toward an audience that speaks a particular language.
- F. None of above. chosen
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_69d827865f608190b311820428ae027b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de612266248190a8591b646fe30ae6 |
completed | April 14, 2026, 3:45 p.m. |
| PD | Predicate disambiguation | batch_69de05b5e7a08190a16be9ad8b92b80c |
completed | April 14, 2026, 9:15 a.m. |
| PDg | Predicate description generation | batch_69de239a02e881909b0e2679487e4ab2 |
completed | April 14, 2026, 11:23 a.m. |
Created at: April 10, 2026, 12:53 a.m.