Triple
T20138824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kersti Kaljulaid |
E491104
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | European Union |
—
|
NE NERFINISHED |
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: European Union | Statement: [Kersti Kaljulaid, employer, European Union]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: European Union Context triple: [Kersti Kaljulaid, employer, European Union]
-
A.
European Union
chosen
The European Union is a political and economic union of European countries that collectively form one of the world’s largest single markets and play a major role in global diplomacy and governance.
-
B.
EU
EU is the vehicle registration code for the German district of Euskirchen in the state of North Rhine-Westphalia.
-
C.
European community
The European community is a diverse population group in Europe characterized by a wide range of nationalities, cultures, and languages sharing common historical, political, and economic ties.
-
D.
ЄС
ЄС is a Ukrainian pro-European political party led by former president Petro Poroshenko that advocates for European integration and democratic reforms.
-
E.
E.U.
E.U. is a Washington, D.C.-based go-go band best known for their 1988 hit single "Da Butt."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667698a188190869c18b925dba2ed |
completed | April 20, 2026, 5:50 p.m. |
Created at: April 11, 2026, 11:32 p.m.