Triple
T14837016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | arms of Savoy |
E348857
|
entity |
| Predicate | typeOfCross |
P67845
|
FINISHED |
| Object | Greek cross |
—
|
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: Greek cross | Statement: [arms of Savoy, typeOfCross, Greek cross]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfCross Context triple: [arms of Savoy, typeOfCross, Greek cross]
-
A.
hasTypeOfCross
chosen
Indicates that an entity possesses or is associated with a specific type or style of cross.
-
B.
traditionalCrossType
Indicates that one entity is related to another through a conventional or historically established type of cross or crossing relationship.
-
C.
crossType
Indicates a relationship where one entity intersects, passes over, or traverses another, typically implying movement or extension across a boundary, area, or medium.
-
D.
crossingType
Indicates the specific kind or category of crossing (e.g., how or where one thing passes over, through, or across another).
-
E.
crossesIn
Indicates that one entity passes over or through the path, boundary, or area occupied by another entity, intersecting its space or trajectory.
- 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_69d822ec69008190a9232caa68836872 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded28d0ddc8190a34e3e2d469ab762 |
completed | April 14, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69de8c13418c819088ff9905ace1416a |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:52 a.m.