Triple
T21427798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dream of the Song |
E528605
|
entity |
| Predicate | textAuthors |
P2353
|
FINISHED |
| Object | medieval Hebrew poets |
—
|
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 Hebrew poets | Statement: [Dream of the Song, textAuthors, medieval Hebrew poets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: textAuthors Context triple: [Dream of the Song, textAuthors, medieval Hebrew poets]
-
A.
targetAuthors
Indicates that certain authors are the intended or designated recipients, subjects, or focus of an action or operation.
-
B.
bookAuthors
chosen
Indicates the relationship between a book and the person or people who authored it.
-
C.
authors
Indicates that one entity is the creator or writer of another entity, such as a document, work, or piece of content.
-
D.
collectionAuthor
Indicates that an entity is the creator or compiler responsible for assembling the items in a collection.
-
E.
authorOfNamesFor
Indicates that one entity is the creator or originator of the names assigned to another entity or set of entities.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b3e63a54819089efea2f26b58107 |
completed | April 22, 2026, 11:41 a.m. |
| PD | Predicate disambiguation | batch_69e61639ee288190889ffd500d1260f6 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 5:49 p.m.