Triple
T2157722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gutenberg Bible copies |
E47929
|
entity |
| Predicate | haveDecoration |
P2788
|
FINISHED |
| Object | hand-illuminated initials in some copies |
—
|
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: hand-illuminated initials in some copies | Statement: [Gutenberg Bible copies, haveDecoration, hand-illuminated initials in some copies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveDecoration Context triple: [Gutenberg Bible copies, haveDecoration, hand-illuminated initials in some copies]
-
A.
typeOfDecoration
chosen
Indicates the specific kind or style of decoration associated with an entity or applied in a given context.
-
B.
hasCeilingDecoration
Indicates that an entity features or is adorned with a decorative element on its ceiling.
-
C.
confersIndividualDecoration
Indicates that an individual is formally awarded a specific decoration, honor, or medal.
-
D.
isWearableDecoration
Indicates that one entity serves as a decorative item intended to be worn on the body by another entity.
-
E.
decorationClass
Indicates that one entity serves as a decorative classification or style category applied to 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_69a88a1d1fd8819088b34990d69a712f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe68fe0c8190beb5db003738a6e5 |
completed | March 7, 2026, 5:58 a.m. |
| PD | Predicate disambiguation | batch_69abbd9a60648190b20b116be5c7ad98 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.