Triple
T34800296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faculty Board of Studies |
E1003200
|
entity |
| Predicate | makesRecommendationTo |
P52897
|
FINISHED |
| Object | Senate on academic matters relating to the Faculty of Science |
—
|
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: Senate on academic matters relating to the Faculty of Science | Statement: [Faculty Board of Studies, makesRecommendationTo, Senate on academic matters relating to the Faculty of Science]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: makesRecommendationTo Context triple: [Faculty Board of Studies, makesRecommendationTo, Senate on academic matters relating to the Faculty of Science]
-
A.
madeRecommendation
chosen
Indicates that one entity has suggested or advised another entity to consider a particular option, action, or choice.
-
B.
canRecommend
Indicates that one entity is able or authorized to suggest or endorse another entity as suitable or preferable.
-
C.
implementsRecommendationOf
Indicates that one entity carries out or puts into practice a recommendation that was proposed or issued by another entity.
-
D.
commendedFor
Indicates that one entity has expressed praise or approval toward another entity specifically because of a particular action, quality, or achievement.
-
E.
recommendedIn
Indicates that one entity is suggested or endorsed within the context, content, or scope of another entity (such as a document, list, or recommendation source).
- 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77a886ac48190a82b0a71a2092028 |
completed | May 3, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.