Semantics ladder

How much does an LLM gain from being told what data means?

The experiment

Goals
Method

Credit ratings

Research analytics

The results

All data is invented: the companies, LEIs, ratings, works, people and institutions. Nothing here is any rating agency's or bibliographic database's data or definitions.

Last updated 6 November 2026.

Q24, run 2026-11-04-1643-sonnet

← back to the run

Is Kestrel Energy's issuer rating investment grade?

Tests: Issuer versus instrument: BBB, at the issuer, even though one note is below investment grade.

Expected: investment_grade = yes

✅ R1 csv run 1 graded by code

Yes. BBB (A02, A03).

JSON: {"investment_grade": "yes"}

✅ R1 csv run 2 graded by code

Yes. Its BBB rating (A03) is investment grade.

JSON: {"investment_grade": "yes"}

✅ R1 csv run 3 graded by code

Yes. The rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R1 csv run 4 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R1 csv run 5 graded by code

Yes. Kestrel's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R2 rdf run 1 graded by code

Yes, BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R2 rdf run 2 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R2 rdf run 3 graded by code

Yes. The LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R2 rdf run 4 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R2 rdf run 5 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R6 rdf+ontology run 1 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R6 rdf+ontology run 2 graded by code

Yes. E01's FC long-term rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R6 rdf+ontology run 3 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R6 rdf+ontology run 4 graded by code

Yes. E01's current rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R6 rdf+ontology run 5 graded by code

Yes. E01's issuer rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R5 csv+ontology run 1 graded by code

Yes. E01's current LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R5 csv+ontology run 2 graded by code

Yes. E01's LTIDR is BBB (A03), which is investment grade.

JSON: {"investment_grade": "yes"}

✅ R5 csv+ontology run 3 graded by code

Yes. E01's LTIDR is BBB (A03), which is investment grade.

JSON: {"investment_grade": "yes"}

✅ R5 csv+ontology run 4 graded by code

Yes. E01's LTIDR FC is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R5 csv+ontology run 5 graded by code

Yes. E01's current LTIDR is BBB (A03), which is investment grade.

JSON: {"investment_grade": "yes"}

✅ R4 csv+markdown run 1 graded by code

Yes. E01's current LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R4 csv+markdown run 2 graded by code

Yes. The LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R4 csv+markdown run 3 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R4 csv+markdown run 4 graded by code

Yes. E01's LTIDR FC is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R4 csv+markdown run 5 graded by code

Yes. The rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R3 csv+padding run 1 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R3 csv+padding run 2 graded by code

Yes. E01's issuer rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R3 csv+padding run 3 graded by code

Yes. E01's issuer rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R3 csv+padding run 4 graded by code

Yes. E01's issuer rating is BBB (A03).

JSON: {"investment_grade": "yes"}

✅ R3 csv+padding run 5 graded by code

Yes. E01's LTIDR is BBB (A03).

JSON: {"investment_grade": "yes"}