Triple
T25338981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gates of Paradise |
E635354
|
entity |
| Predicate | originalPanelsLocation |
P56374
|
FINISHED |
| Object | Museo dell’Opera del Duomo, Florence |
—
|
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: Museo dell’Opera del Duomo, Florence | Statement: [Gates of Paradise, originalPanelsLocation, Museo dell’Opera del Duomo, Florence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalPanelsLocation Context triple: [Gates of Paradise, originalPanelsLocation, Museo dell’Opera del Duomo, Florence]
-
A.
numberOfPanels
Indicates the total count of distinct panels associated with or contained within a given entity.
-
B.
mainLocation
Indicates that one entity serves as the primary or central location associated with another entity.
-
C.
locationOfOriginals
chosen
Indicates the place where the original versions or source items of something are kept or found.
-
D.
centralPanelDepicts
Indicates that the central panel of a multi-part work (such as a triptych or polyptych) visually represents or portrays a particular subject or scene.
-
E.
panelFound
Indicates that a specific panel has been located, identified, or successfully detected in a given context or environment.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f707f7959881908f037f0d6b1d0c36 |
completed | May 3, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_69f700fc274c8190a128593dc7c7abd0 |
completed | May 3, 2026, 8:02 a.m. |
Created at: April 21, 2026, 1:32 p.m.