Triple
T5046034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Kingdom and France |
E113665
|
entity |
| Predicate | shareLegalCooperation |
P38189
|
FINISHED |
| Object | extradition agreements |
—
|
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: extradition agreements | Statement: [United Kingdom and France, shareLegalCooperation, extradition agreements]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shareLegalCooperation Context triple: [United Kingdom and France, shareLegalCooperation, extradition agreements]
-
A.
hasLegalCooperation
chosen
Indicates that one entity engages in formal legal collaboration or assistance with another entity, typically through agreements, joint actions, or shared legal responsibilities.
-
B.
sharesLaw
Indicates that two or more entities are governed by, subject to, or operate under the same law or legal framework.
-
C.
sharesCaseWith
Indicates that two entities are involved in, or associated with, the same legal case or proceeding.
-
D.
lawPartnerOf
Indicates a professional relationship in which two individuals are partners in the same law firm or legal practice.
-
E.
judicialPartner
Indicates a formal partnership or collaborative relationship between entities within a judicial or court-related context.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73fe99688190961708f5d8eb6bff |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd715479f08190933604aebd34414f |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.