Triple
T5933450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AXA |
E131989
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object | AXA XL |
E131989
|
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: AXA XL | Statement: [AXA, subsidiary, AXA XL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AXA XL Context triple: [AXA, subsidiary, AXA XL]
-
A.
AXA
chosen
AXA is a major French multinational insurance and asset management company headquartered in Paris.
-
B.
Swiss Re
Swiss Re is a leading global reinsurance company headquartered in Zurich, Switzerland, providing risk transfer and insurance solutions worldwide.
-
C.
Allianz
Allianz is a leading global financial services company, best known as one of the world’s largest insurance and asset management providers.
-
D.
Munich Re
Munich Re is a leading global reinsurance company based in Germany, known for providing risk management and insurance solutions worldwide.
-
E.
Allstate
Allstate is a major American insurance company best known for its auto and home insurance services and its long-running national advertising campaigns.
- 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_69c0085c55dc8190aa90e242c956e2fa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0389f6fc881909527b928838ffcdd |
completed | March 22, 2026, 6:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0c064d2a4819096085668182cfde1 |
completed | March 23, 2026, 4:24 a.m. |
Created at: March 22, 2026, 4 p.m.