Triple
T10801674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Retirement Solutions |
E254851
|
entity |
| Predicate | brandOf |
P1500
|
FINISHED |
| Object | Aon |
E48249
|
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: Aon | Statement: [Retirement Solutions, brandOf, Aon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aon Context triple: [Retirement Solutions, brandOf, Aon]
-
A.
Aon Corporation
chosen
Aon Corporation is a global professional services firm specializing in risk management, insurance brokerage, and human capital consulting.
-
B.
Chubb
Chubb is a global security and fire-safety solutions company known for providing alarm systems, fire protection, and related services to commercial and residential customers.
-
C.
AIG
AIG (American International Group) is a global insurance and financial services corporation known for its extensive property-casualty, life insurance, and retirement products.
-
D.
Asgrow
Asgrow is a prominent agricultural seed brand, best known for its high-yield soybean and corn varieties marketed to commercial farmers.
-
E.
Kroll
Kroll is a surname most notably associated with Colin Kroll, the American entrepreneur and co-founder of Vine and HQ Trivia.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7336dedec819099bd302c5d213dba |
completed | April 9, 2026, 5:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4417f4dfc8190bd50cec0bc52a9cc |
completed | April 19, 2026, 2:44 a.m. |
Created at: April 8, 2026, 9:18 p.m.