Triple
T5933462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AXA |
E131989
|
entity |
| Predicate | hasGlobalRanking |
P733
|
FINISHED |
| Object | one of the world’s largest insurance companies |
—
|
LITERAL 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: one of the world’s largest insurance companies | Statement: [AXA, hasGlobalRanking, one of the world’s largest insurance companies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGlobalRanking Context triple: [AXA, hasGlobalRanking, one of the world’s largest insurance companies]
-
A.
globalRanking
chosen
Indicates the position or status of an entity relative to all comparable entities worldwide according to some ranking criteria.
-
B.
hasRankingUnit
Indicates that one entity is associated with a specific unit or scale used to express its ranking or ordered position.
-
C.
hasRankingCategory
Indicates that an entity is associated with a particular ranking category or tier within an ordered classification system.
-
D.
hasWorldRankingPoints
Indicates that an entity possesses a certain number of points in a global or international ranking system.
-
E.
hasRankingFactor
Indicates that one entity contributes as a factor to determining the ranking or ordered position of another entity.
- 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_69c0085c55dc8190aa90e242c956e2fa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c03f26f51881908cc253fe5775a1fc |
completed | March 22, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69c03355caf08190b960563a1aed23f9 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 4 p.m.