Triple
T24809717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Seal of Scotland |
E620750
|
entity |
| Predicate | keeper |
P6488
|
FINISHED |
| Object | First Minister of Scotland |
—
|
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: First Minister of Scotland | Statement: [Great Seal of Scotland, keeper, First Minister of Scotland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keeper Context triple: [Great Seal of Scotland, keeper, First Minister of Scotland]
-
A.
keeperType
Indicates the role or category of keeper responsible for an entity, such as what kind of caretaker or guardian it has.
-
B.
firstKeeper
Indicates that the subject is the initial or primary keeper, guardian, or custodian of the object in the relationship.
-
C.
holder
chosen
Indicates that one entity possesses, controls, or has custody of another entity, typically in a temporary or contextual sense.
-
D.
caretakerManagerOf
Indicates that one entity serves as the caretaker or manager responsible for overseeing, maintaining, or looking after another entity.
-
E.
keptIn
Indicates that one entity is stored, contained, or maintained inside another entity as its location or container.
- 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_69e2fabf26bc8190b191faac8f67065b |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f42d9000b8819081ea2605f3c193d6 |
completed | May 1, 2026, 4:35 a.m. |
| PD | Predicate disambiguation | batch_69f420f471a0819095a6cd24ed8f7476 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 4:50 a.m.