Triple
T26376079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agnew’s London gallery |
E660902
|
entity |
| Predicate | principalExhibitionSpaceOf |
P53354
|
FINISHED |
| Object | Thomas Agnew & Sons |
—
|
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: Thomas Agnew & Sons | Statement: [Agnew’s London gallery, principalExhibitionSpaceOf, Thomas Agnew & Sons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: principalExhibitionSpaceOf Context triple: [Agnew’s London gallery, principalExhibitionSpaceOf, Thomas Agnew & Sons]
-
A.
exhibitedBy
Indicates that something (such as a quality, behavior, or characteristic) is shown, displayed, or demonstrated by a particular entity.
-
B.
exhibitionSpaceType
Indicates the specific kind or category of space used to display or present exhibitions.
-
C.
exhibitLocation
chosen
Indicates the place or venue where something is displayed, presented, or put on exhibit.
-
D.
hasExhibitsFrom
Indicates a relationship where one entity (typically a venue or collection) includes or displays exhibits originating from another entity (such as an artist, institution, or location).
-
E.
fieldOfExhibition
Indicates the domain or area in which something is publicly presented, displayed, or exhibited.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 26, 2026, 11:01 p.m.