Triple
T28301756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isabella |
E713726
|
entity |
| Predicate | firstPublicationFormOfWork |
P47750
|
FINISHED |
| Object | poetry collection |
—
|
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: poetry collection | Statement: [Isabella, firstPublicationFormOfWork, poetry collection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPublicationFormOfWork Context triple: [Isabella, firstPublicationFormOfWork, poetry collection]
-
A.
firstPublishedWork
Indicates that one work is the earliest piece created or released by a particular creator or entity.
-
B.
firstPublicationIn
chosen
Indicates the initial venue, medium, or context in which a work was first published.
-
C.
firstPublicationOfContainingWork
Indicates that the related entity is the earliest published work in which the referenced work or content first appeared.
-
D.
firstDraftPublishedIn
Indicates that the first draft of a work was published or made publicly available in a specified venue, medium, or publication.
-
E.
firstPublicationUnderName
Indicates that an entity’s first publication occurred using a specified name (e.g., pseudonym, pen name, or new legal name).
- 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fff4530f908190afe9387f732c2b7e |
completed | May 10, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fff3c01a64819091196875b0c88607 |
completed | May 10, 2026, 2:56 a.m. |
Created at: April 27, 2026, 11:35 p.m.