Triple
T14569111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DELAG |
E341863
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Crédit Lyonnais |
E983687
|
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: Crédit Lyonnais | Statement: [DELAG, foundedBy, Crédit Lyonnais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crédit Lyonnais Context triple: [DELAG, foundedBy, Crédit Lyonnais]
-
A.
Crédit Lyonnais
chosen
Crédit Lyonnais is a major French banking institution, historically state-owned and later privatized, that has played a significant role in France’s financial sector.
-
B.
BNP Paribas
BNP Paribas is a major French international banking group and one of the largest financial institutions in Europe.
-
C.
Société Générale
Société Générale is a major French multinational investment and retail bank and financial services company headquartered in Paris.
-
D.
Carrefour Banque
Carrefour Banque is the financial services subsidiary of the Carrefour retail group, offering products such as credit cards, loans, and savings accounts.
-
E.
Caisse d’Epargne
Caisse d’Epargne was a French professional road cycling team, sponsored by the French savings bank group of the same name, that competed at the highest level of the sport in the 2000s.
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb3f2121481908f2385637944785d |
completed | April 14, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fda91437e08190a41683f1777a8507 |
completed | May 8, 2026, 9:12 a.m. |
Created at: April 10, 2026, 1:23 a.m.