Triple
T30083728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingsfold |
E764542
|
entity |
| Predicate | editorOfFirstMajorHymnal |
P53845
|
FINISHED |
| Object | Ralph Vaughan Williams |
—
|
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: Ralph Vaughan Williams | Statement: [Kingsfold, editorOfFirstMajorHymnal, Ralph Vaughan Williams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editorOfFirstMajorHymnal Context triple: [Kingsfold, editorOfFirstMajorHymnal, Ralph Vaughan Williams]
-
A.
associatedWithHymns
Indicates that something has a connection or relationship to hymns, such as being used in, derived from, or thematically linked to them.
-
B.
editorOfFirstBookPublication
chosen
Indicates that a person or entity served as the editor for the first published edition of a specific book.
-
C.
anthemComposer
Indicates that one entity is the person who composed the anthem associated with another entity.
-
D.
firstHolderInCanon
Indicates that the subject is the earliest entity, in the canonical timeline or storyline, known to have held or possessed the specified object, title, or role.
-
E.
founderWrote
Indicates that an entity who is a founder of something is also the author or writer of a specified work or text.
- 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67d6a9ae08190ba91cbe92980e3f0 |
completed | May 2, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:03 p.m.