Triple
T5001862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamar of Georgia |
E112391
|
entity |
| Predicate | expandedInfluenceOver |
P23136
|
FINISHED |
| Object | Caucasus region |
—
|
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: Caucasus region | Statement: [Tamar of Georgia, expandedInfluenceOver, Caucasus region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expandedInfluenceOver Context triple: [Tamar of Georgia, expandedInfluenceOver, Caucasus region]
-
A.
placeOfInfluence
chosen
Indicates the location or area where an entity exerts significant impact, authority, or cultural, social, or intellectual influence.
-
B.
typeOfInfluence
Indicates the specific nature or category of influence that one entity exerts on another.
-
C.
influenced
Indicates that one entity has affected, shaped, or altered another entity’s state, behavior, or characteristics.
-
D.
hasEnduringInfluenceOn
Indicates that one entity exerts a lasting, long-term impact on another entity’s state, development, or behavior.
-
E.
hasHistoricalInfluenceFrom
Indicates that one entity’s characteristics, development, or significance have been shaped or affected by the past actions, ideas, or legacy of 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_69bd4433d0b08190877e83959ef40d81 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7472a1dc8190942f568a81fdd961 |
completed | March 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69bd714aee2481908fb0dd5fa2daf3a1 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:34 p.m.