Triple
T32535449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Dexter Ward |
E831575
|
entity |
| Predicate | partOfWorkCorpus |
P131077
|
FINISHED |
| Object | works of H. P. Lovecraft |
—
|
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: works of H. P. Lovecraft | Statement: [Charles Dexter Ward, partOfWorkCorpus, works of H. P. Lovecraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfWorkCorpus Context triple: [Charles Dexter Ward, partOfWorkCorpus, works of H. P. Lovecraft]
-
A.
hasPartOfCorpus
Indicates that one entity constitutes a component or segment of the overall corpus associated with another entity.
-
B.
partOfWorkType
Indicates that something is a component, subtype, or specific category within a broader type of work.
-
C.
corpus
Indicates that an entity is a collection or body of texts, documents, or linguistic data used as a unified set for analysis or reference.
-
D.
isPartOfBodyOfWork
chosen
Indicates that one creative work is a component, segment, or installment within a larger overarching body of related work.
-
E.
hasPartInWrittenWork
Indicates that an entity participates in or contributes to the creation of a written work.
- 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_69f34924b1cc8190ad3aca0c0f012a7e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ffb5c373948190a6606e8caa87a384 |
completed | May 9, 2026, 10:31 p.m. |
| PD | Predicate disambiguation | batch_69ffb261da788190b41399df8ed895e8 |
completed | May 9, 2026, 10:17 p.m. |
Created at: May 1, 2026, 1:01 a.m.