Triple
T9978067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De officiis |
E196380
|
entity |
| Predicate | usedAsTextbook |
P25606
|
FINISHED |
| Object | medieval universities |
—
|
LITERAL 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: medieval universities | Statement: [De officiis, usedAsTextbook, medieval universities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsTextbook Context triple: [De officiis, usedAsTextbook, medieval universities]
-
A.
notableTextbook
chosen
Indicates that a textbook is recognized as significant, influential, or widely used within its field or subject area.
-
B.
usesBookAs
Indicates that one entity employs or treats a book as a particular tool, resource, or role in a given context.
-
C.
isStudiedUsing
Indicates that something serves as the method, tool, or approach by which something else is examined, analyzed, or researched.
-
D.
usedAsBookstoreTo
Indicates that one entity functions or is utilized as a bookstore for another entity.
-
E.
usedAsExampleIn
Indicates that one entity is cited or presented as an illustrative example within another entity, such as a text, discussion, or explanation.
- F. None of above.
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_69ca82efbce081908179b4b9c65096eb |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb84ef8ac8190abbe78b7611c5309 |
completed | April 2, 2026, 12:29 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9daa808190b413a1b9a1e929e2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:48 p.m.