Triple
T6323977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ordre du Mérite des Douanes |
E141814
|
entity |
| Predicate | hasRecipientGroup |
P379
|
FINISHED |
| Object | customs officers |
—
|
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: customs officers | Statement: [Ordre du Mérite des Douanes, hasRecipientGroup, customs officers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRecipientGroup Context triple: [Ordre du Mérite des Douanes, hasRecipientGroup, customs officers]
-
A.
hasRecipientWork
Indicates that a work (such as a document, message, or creative piece) is directed or assigned to a specific recipient entity.
-
B.
hasTypeOfRecipient
chosen
Indicates that an entity is associated with a specific category or kind of recipient it is intended for or directed to.
-
C.
hasFirstRecipient
Indicates that an entity is the initial or primary recipient of something (such as a message, award, or transfer) in a sequence or set of recipients.
-
D.
hasRecipientQuality
Indicates that a recipient possesses or is characterized by a particular quality or attribute.
-
E.
hasRelatedGroup
Indicates that one group or collection is associated with another group or collection through some defined relationship or connection.
- 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_69c008d201748190917e69c41ba3f978 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c064e538ac81908c5d7556513c2bc3 |
completed | March 22, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69c060e5efc48190861b8266e5b0cc0c |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:29 p.m.