Triple
T8128591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arron Banks |
E189797
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Arron |
E189797
|
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: Arron | Statement: [Arron Banks, givenName, Arron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arron Context triple: [Arron Banks, givenName, Arron]
-
A.
Aron
Aron is a surname most notably associated with Raymond Aron, a prominent 20th-century French philosopher, sociologist, and political commentator.
-
B.
Aron
Aron was a medieval Bulgarian nobleman and member of the Cometopuli dynasty, known as one of the brothers who resisted Byzantine rule in the late 10th century.
-
C.
Aron
Aron is a river in central France that joins the Loire near the town of Decize.
-
D.
Aron Julius
Aron Julius is an actor known for his role in the German television series "Cucumber."
-
E.
Arron Banks
chosen
Arron Banks is a British businessman and political donor best known for bankrolling and co-founding the pro-Brexit campaign group Leave.EU.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82bcb4848190a9a9d036ad768642 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb439190d88190aa614445c7479353 |
completed | March 31, 2026, 3:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc947303f881908e16af664fb74dc8 |
completed | April 1, 2026, 3:43 a.m. |
Created at: March 30, 2026, 5:34 p.m.