Triple
T31957670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Les Sources de Caudalie |
E815950
|
entity |
| Predicate | hasTargetClientele |
P82339
|
FINISHED |
| Object | luxury travelers |
—
|
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: luxury travelers | Statement: [Les Sources de Caudalie, hasTargetClientele, luxury travelers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTargetClientele Context triple: [Les Sources de Caudalie, hasTargetClientele, luxury travelers]
-
A.
hadClientele
Indicates that an entity regularly served or catered to a particular group of clients or customers.
-
B.
hasMarketingTarget
Indicates that an entity is aimed at or intended to appeal to a specific marketing audience or segment.
-
C.
hasTargetVisitors
Indicates that something is intended or designed to be visited by a specific group of people as its primary audience or users.
-
D.
intendedClients
chosen
Indicates the entities that a product, service, or action is specifically designed or targeted to serve as clients.
-
E.
hasTargetMarketPositioning
Indicates the specific market segment and competitive position that an offering is intended to occupy relative to alternatives.
- 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f969b4cc8190afb473a2d8b110bc |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 12:08 a.m.