Triple
T5439846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boylston Professor of Rhetoric and Oratory at Harvard University |
E122102
|
entity |
| Predicate | isProfessorshipIn |
P64076
|
FINISHED |
| Object | Department of English at Harvard University |
E520527
|
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: Department of English at Harvard University | Statement: [Boylston Professor of Rhetoric and Oratory at Harvard University, isProfessorshipIn, Department of English at Harvard University]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Department of English at Harvard University Context triple: [Boylston Professor of Rhetoric and Oratory at Harvard University, isProfessorshipIn, Department of English at Harvard University]
-
A.
Harvard University Department of English
chosen
The Harvard University Department of English is the academic unit responsible for teaching and research in English literature, language, and related fields at Harvard University.
-
B.
Department of Comparative Literature at Harvard University
The Department of Comparative Literature at Harvard University is an academic unit that fosters interdisciplinary and cross-cultural literary study, bringing together languages, traditions, and theoretical approaches from around the world.
-
C.
Department of Romance Languages and Literatures at Harvard University
The Department of Romance Languages and Literatures at Harvard University is an academic department dedicated to the study, teaching, and research of Romance languages, literatures, and cultures such as French, Italian, Portuguese, and Spanish.
-
D.
Faculty of Arts and Sciences, Harvard University
The Faculty of Arts and Sciences at Harvard University is the main academic division that oversees Harvard College, the Graduate School of Arts and Sciences, and several other schools, encompassing the university’s core liberal arts and sciences teaching and research.
-
E.
Faculty of English, University of Cambridge
The Faculty of English at the University of Cambridge is a leading academic department renowned for its teaching and research in English literature, language, and related fields.
- 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: isProfessorshipIn Context triple: [Boylston Professor of Rhetoric and Oratory at Harvard University, isProfessorshipIn, Department of English at Harvard University]
-
A.
hasUniversityFaculty
Indicates that a university or academic institution employs or is associated with one or more faculty members.
-
B.
hasFaculty
Indicates that an institution or department possesses or is associated with one or more faculty members.
-
C.
hasTeachingRole
Indicates that one entity holds a position or responsibility involving teaching or instruction in relation to another entity.
-
D.
isPublicUniversityFaculty
Indicates that a person holds a faculty position at a public (state- or government-funded) university.
-
E.
hasAcademicFunction
Indicates that an entity serves a specific academic role, duty, or function within an educational or scholarly context.
- F. None of above. chosen
Provenance (5 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_69bd46400768819092925d461c0b8432 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd922f66bc8190b7d47fd68d2fcf2e |
completed | March 20, 2026, 6:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf487fdfe08190af6294021d1b81e5 |
completed | March 22, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69bd919aeb048190b786f814177d6cd9 |
completed | March 20, 2026, 6:27 p.m. |
| PDg | Predicate description generation | batch_69bd922dc688819092bf33589ebc6d50 |
completed | March 20, 2026, 6:30 p.m. |
Created at: March 20, 2026, 2:07 p.m.