Triple
T20022803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gresham College |
E494903
|
entity |
| Predicate | hasNotableProfessor |
P13831
|
FINISHED |
| Object | Jeremy Black |
—
|
NE NERFINISHED |
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: Jeremy Black | Statement: [Gresham College, hasNotableProfessor, Jeremy Black]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeremy Black Context triple: [Gresham College, hasNotableProfessor, Jeremy Black]
-
A.
Jeremy Black
chosen
Jeremy Black is a British historian renowned for his prolific scholarship on military history, international relations, and the history of warfare.
-
B.
David A. Black
David A. Black is a Ruby programmer, author, and educator best known for his influential books and contributions to the Ruby community.
-
C.
David Blackman
David Blackman is a film and television producer known for his executive production work on music-related documentaries and projects.
-
D.
David L. Black
David L. Black is a computer scientist and networking expert known for his contributions to Internet standards, including work on early congestion control mechanisms in TCP/IP.
-
E.
John Blackmore
John Blackmore was the father of Victorian novelist Richard Doddridge Blackmore, best known as the author of "Lorna Doone."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66288fc18819083833b55c5e069a6 |
completed | April 20, 2026, 5:29 p.m. |
Created at: April 11, 2026, 3:35 p.m.