Triple
T15496122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady Mary Coke |
E378821
|
entity |
| Predicate | sourceOfInformationOn |
P41259
|
FINISHED |
| Object | Georgian high society |
—
|
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: Georgian high society | Statement: [Lady Mary Coke, sourceOfInformationOn, Georgian high society]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceOfInformationOn Context triple: [Lady Mary Coke, sourceOfInformationOn, Georgian high society]
-
A.
usesInformationSources
Indicates that an entity relies on or consults specified information sources to perform actions, make decisions, or obtain knowledge.
-
B.
providedInformationOn
Indicates that one entity supplied or communicated specific information or details to another entity.
-
C.
collectsInformationOn
chosen
Indicates that one entity gathers or acquires data, facts, or details about another entity.
-
D.
isOfficialSourceFor
Indicates that one entity is recognized as an authoritative or formally sanctioned provider of information or content about another entity.
-
E.
sourceForLife
Indicates that one entity serves as the origin, provider, or sustaining basis of life for 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_69d85cd53a7c819080f5b9042c4c199e |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03faecd60819091eeaa56c9c8f67d |
completed | April 16, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69ded2874b788190999158e0f043be21 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:52 a.m.