Q37, run 2026-11-04-1711-sonnet

← back to the run

How many distinct legal entities does the data describe?

Tests: Identity: records with the same LEI are one entity.

Expected: count = 16

❌ R1 csv run 1 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R1 csv run 2 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R1 csv run 3 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R1 csv run 4 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R1 csv run 5 graded by code

17. There are 19 records, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R2 rdf run 1 graded by code

17. There are 19 entity records, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R2 rdf run 2 graded by code

17. There are 19 entity records, but E17 duplicates E10 and E03 duplicates E02, going by their shared LEIs.

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R2 rdf run 3 graded by code

17. There are 19 records, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R2 rdf run 4 graded by code

17. There are 19 entity records, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R2 rdf run 5 graded by code

17. There are 19 entity records. E03 duplicates E02 and E17 duplicates E10, both by shared LEI.

JSON: {"count": 17}

Why: count: expected 16, got 17

✅ R6 rdf+ontology run 1 graded by code

16. The data has 19 entity records. E03 duplicates E02 and E17 duplicates E10, which leaves 17. E16 is a QA record and is excluded, which leaves 16.

JSON: {"count": 16}

✅ R6 rdf+ontology run 2 graded by code

16. The 19 records include two duplicates (E03 is E02, E17 is E10) and one QA record (E16).

JSON: {"count": 16}

✅ R6 rdf+ontology run 3 graded by code

16. There are 19 entity records. Merging E17 into E10 and E03 into E02 removes two, and the QA record E16 is excluded.

JSON: {"count": 16}

✅ R6 rdf+ontology run 4 graded by code

16. There are 19 records (E01–E17, VD, CV). E03 duplicates E02 and E17 duplicates E10, and E16 is QA, which leaves 16.

JSON: {"count": 16}

✅ R6 rdf+ontology run 5 graded by code

16. There are 19 records. E03 duplicates E02 and E17 duplicates E10, which leaves 17. E16 is a QA record and is ignored.

JSON: {"count": 16}

✅ R5 csv+ontology run 1 graded by code

16. There are 19 records. E03 and E17 duplicate E02 and E10, and E16 is QA, leaving 16 including the two sovereigns.

JSON: {"count": 16}

✅ R5 csv+ontology run 2 graded by code

16. There are 19 records, minus 2 duplicates (E03, E17) and 1 QA record (E16).

JSON: {"count": 16}

✅ R5 csv+ontology run 3 graded by code

16. There are 19 records. E16 is QA, and E03 and E17 duplicate E02 and E10 by LEI.

JSON: {"count": 16}

✅ R5 csv+ontology run 4 graded by code

16. There are 19 records. E03 and E17 duplicate E02 and E10 by LEI, and E16 is QA, which leaves 16 including the two sovereigns.

JSON: {"count": 16}

✅ R5 csv+ontology run 5 graded by code

16. There are 19 records; E03 and E17 duplicate E02 and E10, and E16 is QA.

JSON: {"count": 16}

✅ R4 csv+markdown run 1 graded by code

16. The 19 records include two duplicates (E03 and E17) and one QA record (E16).

JSON: {"count": 16}

✅ R4 csv+markdown run 2 graded by code

16. There are 19 records. E03 and E17 duplicate E02 and E10, and E16 is QA, which leaves 16.

JSON: {"count": 16}

✅ R4 csv+markdown run 3 graded by code

16. The 19 records contain two duplicates (E03 is E02, and E17 is E10) and one QA record (E16).

JSON: {"count": 16}

✅ R4 csv+markdown run 4 graded by code

16. There are 19 records, minus the duplicates E03 and E17 and the QA record E16.

JSON: {"count": 16}

✅ R4 csv+markdown run 5 graded by code

16. The data has 19 records. E03 and E17 duplicate E02 and E10, and E16 is QA and ignored.

JSON: {"count": 16}

❌ R3 csv+padding run 1 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R3 csv+padding run 2 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R3 csv+padding run 3 graded by code

17. The file has 19 rows, but E03 duplicates E02 and E17 duplicates E10, both by LEI.

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R3 csv+padding run 4 graded by code

17. The file has 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17

❌ R3 csv+padding run 5 graded by code

17. There are 19 rows, but E03 duplicates E02 and E17 duplicates E10 (same LEIs).

JSON: {"count": 17}

Why: count: expected 16, got 17