Triple
T14503942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sherman Weissman |
E340214
|
entity |
| Predicate | notableStudent |
P4838
|
FINISHED |
| Object | Francis Collins |
E10453
|
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: Francis Collins | Statement: [Sherman Weissman, notableStudent, Francis Collins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Francis Collins Context triple: [Sherman Weissman, notableStudent, Francis Collins]
-
A.
Francis Collins
chosen
Francis Collins is an American physician-geneticist best known for leading the Human Genome Project and serving as director of the U.S. National Institutes of Health.
-
B.
Eric Lander
Eric Lander is an American geneticist and mathematician best known as a principal leader of the Human Genome Project and a founding director of the Broad Institute.
-
C.
Marshall Kirk McKusick
Marshall Kirk McKusick is an American computer scientist best known for his pioneering work on the BSD Unix operating system and its filesystems.
-
D.
Paul Westhead
Paul Westhead is an American basketball coach known for his fast-paced "run-and-gun" offensive style and for winning championships in both the NBA and WNBA.
-
E.
Ezekiel Emanuel
Ezekiel Emanuel is an American oncologist, bioethicist, and health policy expert known for his influential work on medical ethics and U.S. healthcare reform.
- 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de94e0f9048190a2d266cfa4f9dfb6 |
completed | April 14, 2026, 7:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd6d9dba1081909154362b922a2417 |
completed | May 8, 2026, 4:59 a.m. |
Created at: April 10, 2026, 1:21 a.m.