Triple
T34946819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lansdowne collection |
E1007876
|
entity |
| Predicate | containsWorkDepicting |
P185664
|
FINISHED |
| Object | Virgin Mary |
—
|
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: Virgin Mary | Statement: [Lansdowne collection, containsWorkDepicting, Virgin Mary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsWorkDepicting Context triple: [Lansdowne collection, containsWorkDepicting, Virgin Mary]
-
A.
depictionIncludes
chosen
Indicates that a depiction (such as an image, illustration, or visual representation) contains or shows the referenced entity as part of its visual content.
-
B.
isDepictedVia
Indicates that one entity is represented, illustrated, or shown by means of another entity, such as a specific medium, style, or method of depiction.
-
C.
workOftenDepicts
Indicates that one entity’s work frequently portrays, represents, or includes the other entity as a subject or theme.
-
D.
primaryDepictionWork
Indicates that a work is the main or most significant subject depicted in a given representation or resource.
-
E.
supportsDepictionOf
Indicates that one entity provides the medium, context, or framework that enables the depiction or representation of 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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0091ad8b8c8190b0f00a3358e59bc1 |
completed | May 10, 2026, 2:09 p.m. |
| PD | Predicate disambiguation | batch_6a008f2813ec81909a54c2dfa5c75dc7 |
completed | May 10, 2026, 1:59 p.m. |
Created at: May 3, 2026, 4 p.m.