Triple
T1036661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seamus Heaney |
E22377
|
entity |
| Predicate | positionHeld |
P8
|
FINISHED |
| Object |
Boylston Professor of Rhetoric and Oratory at Harvard University
The Boylston Professor of Rhetoric and Oratory at Harvard University is a prestigious endowed chair in the English department historically held by distinguished scholars and writers in the fields of rhetoric, oratory, and literature.
|
E122102
|
NE FINISHED |
How this triple was built (4 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: Boylston Professor of Rhetoric and Oratory at Harvard University | Statement: [Seamus Heaney, positionHeld, Boylston Professor of Rhetoric and Oratory at Harvard University]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boylston Professor of Rhetoric and Oratory at Harvard University Context triple: [Seamus Heaney, positionHeld, Boylston Professor of Rhetoric and Oratory at Harvard University]
-
A.
Smith Professor of Modern Languages at Harvard University
The Smith Professor of Modern Languages at Harvard University is a prestigious endowed chair in the university’s Department of Romance Languages and Literatures, historically associated with leading scholars such as poet and critic James Russell Lowell.
-
B.
Interim President of Harvard University
The Interim President of Harvard University is the temporary chief executive officer of Harvard, responsible for overseeing the university’s academic, administrative, and financial operations during a leadership transition.
-
C.
Smith Professor of the History of Fine Arts at Harvard University
The Smith Professor of the History of Fine Arts at Harvard University is a prestigious endowed chair in art history at Harvard, historically associated with leading scholars such as Charles Eliot Norton.
-
D.
Professor at Massachusetts Institute of Technology
Professor at the Massachusetts Institute of Technology is an academic position held by faculty members who teach, conduct research, and contribute to scholarship at the renowned science and engineering-focused university in Cambridge, Massachusetts.
-
E.
Institute Professor at MIT
Institute Professor at MIT is the highest faculty rank at the Massachusetts Institute of Technology, reserved for a small number of exceptionally distinguished scholars recognized for outstanding contributions to their fields.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Boylston Professor of Rhetoric and Oratory at Harvard University Triple: [Seamus Heaney, positionHeld, Boylston Professor of Rhetoric and Oratory at Harvard University]
Generated description
The Boylston Professor of Rhetoric and Oratory at Harvard University is a prestigious endowed chair in the English department historically held by distinguished scholars and writers in the fields of rhetoric, oratory, and literature.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Boylston Professor of Rhetoric and Oratory at Harvard University Target entity description: The Boylston Professor of Rhetoric and Oratory at Harvard University is a prestigious endowed chair in the English department historically held by distinguished scholars and writers in the fields of rhetoric, oratory, and literature.
-
A.
Smith Professor of Modern Languages at Harvard University
The Smith Professor of Modern Languages at Harvard University is a prestigious endowed chair in the university’s Department of Romance Languages and Literatures, historically associated with leading scholars such as poet and critic James Russell Lowell.
-
B.
Higgins Professor of Physics at Harvard University
The Higgins Professor of Physics at Harvard University is a prestigious endowed chair in the university’s physics department, historically associated with leading theoretical physicists such as Nobel laureate Sheldon Glashow.
-
C.
Interim President of Harvard University
The Interim President of Harvard University is the temporary chief executive officer of Harvard, responsible for overseeing the university’s academic, administrative, and financial operations during a leadership transition.
-
D.
University Professor at Boston University
University Professor at Boston University is a prestigious senior academic title awarded to distinguished scholars at Boston University in recognition of exceptional achievement and impact in their fields.
-
E.
Smith Professor of the History of Fine Arts at Harvard University
The Smith Professor of the History of Fine Arts at Harvard University is a prestigious endowed chair in art history at Harvard, historically associated with leading scholars such as Charles Eliot Norton.
- 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_69a493d848848190aed4011b34b2e8d3 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b82a1014819085bfc077e24c9742 |
completed | March 1, 2026, 10:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac3bc378fc8190846d5ffce73371dd |
completed | March 7, 2026, 2:52 p.m. |
| NEDg | Description generation | batch_69ac3df28858819091c594a9cb2aab07 |
completed | March 7, 2026, 3:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac3e5b716c8190b95fde14ee6c434a |
completed | March 7, 2026, 3:03 p.m. |
Created at: March 1, 2026, 7:41 p.m.