Triple
T19695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cairo University |
E391
|
entity |
| Predicate | hasInstitute |
P186
|
FINISHED |
| Object | National Cancer Institute |
E2622
|
NE FINISHED |
How this triple was built (3 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: National Cancer Institute | Statement: [Cairo University, hasInstitute, National Cancer Institute]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: National Cancer Institute Context triple: [Cairo University, hasInstitute, National Cancer Institute]
-
A.
National Cancer Institute
chosen
The National Cancer Institute is the U.S. federal government’s principal agency for cancer research and training, leading nationwide efforts to prevent, diagnose, and treat cancer.
-
B.
Memorial Sloan Kettering Cancer Center
Memorial Sloan Kettering Cancer Center is a world-renowned cancer treatment and research institution based in New York City, known for its pioneering work in oncology and biomedical science.
-
C.
National Institutes of Health
The National Institutes of Health is the United States’ primary federal biomedical research agency, supporting and conducting medical research to improve public health.
-
D.
American Association for Cancer Research
The American Association for Cancer Research is a leading professional organization dedicated to advancing cancer research, prevention, diagnosis, and treatment through scientific collaboration and dissemination of findings.
-
E.
Rockefeller University
Rockefeller University is a prestigious private biomedical research university in New York City renowned for its pioneering contributions to life sciences and medicine.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInstitute Context triple: [Cairo University, hasInstitute, National Cancer Institute]
-
A.
hasAcademicAffiliation
Indicates that an entity is formally associated with an academic institution, such as through employment, enrollment, or official collaboration.
-
B.
hostsInstitution
chosen
Indicates that one entity serves as the hosting location or organizing body for an institution.
-
C.
workInstitution
Indicates that an entity is employed by or works at a particular institution.
-
D.
hasFaculty
Indicates that an institution or department possesses or is associated with one or more faculty members.
-
E.
hasAcademicDepartment
Indicates that an institution or organization includes or is associated with a specific academic department.
- F. None of above.
Provenance (4 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_69a240778d288190815c0052ebbbcc91 |
completed | Feb. 28, 2026, 1:10 a.m. |
| NER | Named-entity recognition | batch_69a24703cb988190ad2bc181d27829e4 |
completed | Feb. 28, 2026, 1:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a25aaf595c8190b1f6b559f49efd7f |
completed | Feb. 28, 2026, 3:02 a.m. |
| PD | Predicate disambiguation | batch_69a24650f1f0819081e638fafd18d687 |
completed | Feb. 28, 2026, 1:35 a.m. |
Created at: Feb. 28, 2026, 1:14 a.m.