Triple
T4833593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dumitru Erhan |
E108002
|
entity |
| Predicate | isAuthorOf |
P29721
|
FINISHED |
| Object | research papers on deep learning |
—
|
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: research papers on deep learning | Statement: [Dumitru Erhan, isAuthorOf, research papers on deep learning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAuthorOf Context triple: [Dumitru Erhan, isAuthorOf, research papers on deep learning]
-
A.
hasAuthor
Indicates that an entity is written or created by a specific author.
-
B.
hasAuthorPublished
Indicates that a specific author has produced and made publicly available at least one work, such as a book, article, or paper.
-
C.
hasAuthorRelationship
chosen
Indicates a relationship where one entity serves as the author or creator of another entity (such as a work, document, or resource).
-
D.
workOfAuthorOf
Indicates that one entity is a work (such as a book, article, or artwork) created by the author associated with another entity.
-
E.
publishedAuthor
Indicates that a person is the author of one or more works that have been formally published.
- 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_69bd43fbe444819085cb970706ef73f7 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c21c7f08190846049d31fdfa144 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:25 p.m.