Triple
T23568493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hob. XXI:3 |
E580034
|
entity |
| Predicate | workTextAuthor |
P85542
|
FINISHED |
| Object | Gottfried van Swieten |
—
|
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: Gottfried van Swieten | Statement: [Hob. XXI:3, workTextAuthor, Gottfried van Swieten]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workTextAuthor Context triple: [Hob. XXI:3, workTextAuthor, Gottfried van Swieten]
-
A.
workAuthorIs
chosen
Indicates that a specific person or entity is the author or creator of a particular work.
-
B.
theoreticalTextAuthor
Indicates that one entity is the author or creator of a theoretical or conceptual text associated with the other entity.
-
C.
workOfAuthorWho
Indicates that one entity is a work (such as a book, article, or artwork) created by another entity who is its author.
-
D.
workAuthorFullTitle
Indicates that the full title of a work is associated with its author in a complete, non-abbreviated form.
-
E.
workOfAuthorOf
Indicates that one entity is a work (such as a book, article, or artwork) created by the author associated with another entity.
- 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_69e24601a9108190bc31e83833c980e4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1af6e11008190bdd28c3f85e3004e |
completed | April 29, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69f118bcc0b08190b25a8dddfd461a0e |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:35 p.m.