Triple
T23668799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petworth House art collection |
E584665
|
entity |
| Predicate | strongInGenre |
P10232
|
FINISHED |
| Object | British portrait painting |
—
|
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: British portrait painting | Statement: [Petworth House art collection, strongInGenre, British portrait painting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strongInGenre Context triple: [Petworth House art collection, strongInGenre, British portrait painting]
-
A.
hasGenreStrength
chosen
Indicates that something possesses a particular intensity or degree of emphasis associated with a specific genre.
-
B.
promotesGenre
Indicates that one entity actively supports, advertises, or increases the visibility of a particular genre.
-
C.
targetGenre
Indicates the genre that something is specifically aimed at, categorized under, or intended to belong to.
-
D.
namedForGenre
Indicates that something is given a name based on or derived from a particular genre.
-
E.
favoriteGenre
Indicates that one entity’s preferred or most liked genre, among several possible genres, is the other 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_69e24901421881908c17a5293bdd4a8e |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b40d0e208190969fecbede5979b8 |
completed | April 29, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:50 p.m.