Triple
T22460739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mutuelle de L’assurance contre L’incendie |
E555221
|
entity |
| Predicate | predecessorOf |
P97
|
FINISHED |
| Object | AXA |
—
|
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: AXA | Statement: [Mutuelle de L’assurance contre L’incendie, predecessorOf, AXA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AXA Context triple: [Mutuelle de L’assurance contre L’incendie, predecessorOf, AXA]
-
A.
AXA
chosen
AXA is a major French multinational insurance and asset management company headquartered in Paris.
-
B.
Allianz
Allianz is a leading global financial services company, best known as one of the world’s largest insurance and asset management providers.
-
C.
Vaudoise Assurances
Vaudoise Assurances is a Swiss insurance company known for offering a wide range of insurance and financial services and for its prominent sponsorship activities in Swiss sports and culture.
-
D.
BNP Paribas Cardif
BNP Paribas Cardif is the insurance subsidiary of the BNP Paribas banking group, specializing in savings and protection insurance solutions worldwide.
-
E.
Groupama
Groupama is a major French mutual insurance and financial services group known for its extensive network and sponsorship activities in sports and culture.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7eb5688190bd5e41d4d8189668 |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.