Triple
T24295274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Union officials |
E605941
|
entity |
| Predicate | speakOnBehalfOf |
P114929
|
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: [European Union officials, speakOnBehalfOf, European Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speakOnBehalfOf Context triple: [European Union officials, speakOnBehalfOf, European Union]
-
A.
speaksFor
chosen
Indicates that one entity expresses views, decisions, or positions on behalf of another entity.
-
B.
presentedOnBehalfOf
Indicates that an action, statement, or presentation was made by one party while formally representing or acting for another party.
-
C.
actsOnBehalfOf
Indicates that one entity performs actions or makes decisions as a representative or proxy for another entity.
-
D.
appointedOnBehalfOf
Indicates that an appointment or designation is made by one party acting in representation of, or for the benefit of, another party.
-
E.
builtOnBehalfOf
Indicates that something was constructed or created by one party acting as a representative or agent for another party.
- 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_69e29549335881909cbf27adcaba1cf0 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f291593c0881908a6827f0d8899fe6 |
completed | April 29, 2026, 11:16 p.m. |
| PD | Predicate disambiguation | batch_69f1c45c6ec081908401b69424428100 |
completed | April 29, 2026, 8:42 a.m. |
Created at: April 18, 2026, 12:09 a.m.