Triple
T28246960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safdar Jang |
E712193
|
entity |
| Predicate | architecturalStyleOfTomb |
P607
|
FINISHED |
| Object | late Mughal architecture |
—
|
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: late Mughal architecture | Statement: [Safdar Jang, architecturalStyleOfTomb, late Mughal architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: architecturalStyleOfTomb Context triple: [Safdar Jang, architecturalStyleOfTomb, late Mughal architecture]
-
A.
associatedWithTombDecorationStyle
Indicates a relationship where something is linked to, characterized by, or connected with a particular style of tomb decoration.
-
B.
architecturalStyle
chosen
Indicates the architectural design tradition, movement, or style that characterizes the form and appearance of a structure or built work.
-
C.
tombDecoration
Indicates that something serves as an ornamental or symbolic adornment associated with a tomb.
-
D.
hasMausoleum
Indicates that one entity possesses, contains, or is associated with a mausoleum dedicated to another entity.
-
E.
architecturalStyleCombines
Indicates that something incorporates elements or characteristics from multiple architectural styles into a single design.
- 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_69efb51fb98881909692421959ec0170 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f969b4cc8190afb473a2d8b110bc |
completed | May 3, 2026, 7:29 a.m. |
Created at: April 27, 2026, 11:02 p.m.