Q1, run 2026-11-05-1235-haiku

← back to the run

How many distinct people do the author records named "Mara Ellison", "M. Ellison" and "Ellison, Mara J." stand for?

Tests: Identity: A01, A02 and A03 share an ORCID; A04, also 'M. Ellison', has another.

Expected: count = 2

❌ R1 csv run 1 graded by code

1 person. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229, so they are one person; A04 has a different ORCID.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R1 csv run 2 graded by code

1 person: A01, A02 and A03 share ORCID 0000-0002-9841-6229. A04 has a different ORCID.
*Reasoning:* A01–A03 have the same ORCID, while A04 ("M. Ellison") has 0000-0004-8662-8360.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R1 csv run 3 graded by code

1. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. (A04 has a different ORCID.)

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R1 csv run 4 graded by code

1 person. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229, while A04 "M. Ellison" has a different ORCID.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R1 csv run 5 graded by code

1. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229. A04 ("M. Ellison") has a different ORCID, so it is a different person.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R2 rdf run 1 graded by code

2 people. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person; A04 has a different ORCID (0000-0004-8662-8360).

JSON: {"count": 2}

❌ R2 rdf run 2 graded by code

1. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229. A04 ("M. Ellison") has a different ORCID, but it isn't one of the three names asked about.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R2 rdf run 3 graded by code

2 people. A01, A02 and A03 share ORCID 0000-0002-9841-6229, but A04 "M. Ellison" has ORCID 0000-0004-8662-8360.

JSON: {"count": 2}

❌ R2 rdf run 4 graded by code

1. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229, so they are one person. A04 ("M. Ellison") has a different ORCID and is not in this group.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R2 rdf run 5 graded by code

2 distinct people. A01, A02 and A03 share ORCID 0000-0002-9841-6229, while A04 ("M. Ellison") has ORCID 0000-0004-8662-8360.

JSON: {"count": 2}

✅ R6 rdf+ontology run 1 graded by code

2 distinct people. A01, A02 and A03 share ORCID 0000-0002-9841-6229 (one person), while A04 ("M. Ellison") has ORCID 0000-0004-8662-8360.

JSON: {"count": 2}

❌ R6 rdf+ontology run 2 graded by code

1 person. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229, so they are one person.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R6 rdf+ontology run 3 graded by code

1. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 ("M. Ellison") has a different ORCID, so it is not counted.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R6 rdf+ontology run 4 graded by code

1. Author records A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person; A04 ("M. Ellison") has a different ORCID.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R6 rdf+ontology run 5 graded by code

2. A01, A02 and A03 share ORCID 0002-9841-6229, so they are one person; A04 ("M. Ellison", ORCID 0004-8662-8360) is a different person.

JSON: {"count": 2}

❌ R5 csv+ontology run 1 graded by code

1. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R5 csv+ontology run 2 graded by code

1. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 has a different ORCID.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R5 csv+ontology run 3 graded by code

2. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04, also named "M. Ellison", has a different ORCID (0000-0004-8662-8360), so it is a second person.

JSON: {"count": 2}

✅ R5 csv+ontology run 4 graded by code

2. The records A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 is also named "M. Ellison" but has a different ORCID (0000-0004-8662-8360), so it is a second person.

JSON: {"count": 2}

❌ R5 csv+ontology run 5 graded by code

1. A01, A02 and A03 all carry ORCID 0000-0002-9841-6229, so they are one person.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R4 csv+markdown run 1 graded by code

2 people. A01, A02 and A03 share ORCID 0000-0002-9841-6229; A04 has a different ORCID (0000-0004-8662-8360).

JSON: {"count": 2}

✅ R4 csv+markdown run 2 graded by code

2. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 has a different ORCID, so it is a second person.

JSON: {"count": 2}

✅ R4 csv+markdown run 3 graded by code

2 people. A01, A02 and A03 share ORCID 0000-0002-9841-6229, while A04 ("M. Ellison", 0000-0004-8662-8360) is a different person.

JSON: {"count": 2}

✅ R4 csv+markdown run 4 graded by code

2. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 ("M. Ellison") has a different ORCID (0000-0004-8662-8360), so it is a second person.

JSON: {"count": 2}

❌ R4 csv+markdown run 5 graded by code

1 person. A01, A02 and A03 share ORCID 0000-0002-9841-6229; A04 ("M. Ellison") has a different ORCID.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R3 csv+padding run 1 graded by code

2 people. A01, A02 and A03 share ORCID 0000-0002-9841-6229, but A04 ("M. Ellison") has a different ORCID, 0000-0004-8662-8360.

JSON: {"count": 2}

❌ R3 csv+padding run 2 graded by code

1. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 has a different ORCID and is not one of the three named records.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R3 csv+padding run 3 graded by code

2. A01, A02 and A03 share ORCID 0000-0002-9841-6229, so they are one person. A04 ("M. Ellison") has a different ORCID, 0000-0004-8662-8360, so it is a second person.

JSON: {"count": 2}

❌ R3 csv+padding run 4 graded by code

1. A01, A02 and A03 share ORCID 0000-0002-9841-6229; A04 has a different ORCID, so it is a different person.

JSON: {"count": 1}

Why: count: expected 2, got 1

❌ R3 csv+padding run 5 graded by code

One person. A01, A02 and A03 share ORCID 0000-0002-9841-6229; A04 ("M. Ellison") has a different ORCID.

JSON: {"count": 1}

Why: count: expected 2, got 1

✅ R10 executed run 1 graded by code

2 (A01 and A04). A01 and A04 have different ORCIDs, so they are separate people. "Ellison, Mara J." does not appear in people.csv, so I can't place it; it would be A01 only if it is A02 or A03, which are merged into A01 but not shown.

JSON: {"count": 2}

✅ R10 executed run 2 graded by code

2 people: A01 (Mara Ellison, which absorbs author records A02 and A03) and A04 (M. Ellison). A04 has a different ORCID and is its own person. "Ellison, Mara J." does not appear in the data, so I cannot place it.

JSON: {"count": 2}

✅ R10 executed run 3 graded by code

Two: A01 (Mara Ellison) and A04 (M. Ellison). The third name, "Ellison, Mara J.", does not appear in people.csv, so I can't place it; if it is A02 or A03 (merged into A01, names not shown), it is still A01.

JSON: {"count": 2}

✅ R10 executed run 4 graded by code

2 (A01 and A04). The data has no record named "Ellison, Mara J."; A02 and A03 are merged into A01, and A04 has a different ORCID from A01.

JSON: {"count": 2}

✅ R10 executed run 5 graded by code

2 (A01 and A04). A01 (Mara Ellison) already absorbs A02 and A03, and A04 (M. Ellison) has a different ORCID. The data gives no name for "Ellison, Mara J.", so I can't confirm which record it is; if it is A02 or A03, it's already in A01.

JSON: {"count": 2}