Triple
T36638593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMVI |
E904524
|
entity |
| Predicate | supportsCooperationWith |
P98968
|
FINISHED |
| Object | Frontex |
E172041
|
NE 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: Frontex | Statement: [BMVI, supportsCooperationWith, Frontex]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsCooperationWith Context triple: [BMVI, supportsCooperationWith, Frontex]
-
A.
supportsCooperative
chosen
Indicates that one entity provides assistance, resources, or endorsement to enable or strengthen another entity’s cooperative activities or partnerships.
-
B.
supportsCollaborationFeature
Indicates that one entity provides or enables a collaboration-related feature for another entity or within a system.
-
C.
hasCooperative
Indicates that one entity participates in a cooperative relationship or partnership with another entity.
-
D.
implementedInCooperationWith
Indicates that an action, project, or initiative was carried out jointly or collaboratively together with another party.
-
E.
definesCooperationWith
Indicates that one entity formally specifies or establishes the terms, scope, or nature of cooperative interaction with another entity.
- F. None of above.
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_69f76e6c63e48190b1d0c3a79a6c7406 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3c171a3dcc8190a3f582d4b13beff2 |
completed | June 24, 2026, 5:42 p.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:11 p.m.