Triple
T86743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gori |
E1743
|
entity |
| Predicate | wasOccupiedBy |
P3259
|
FINISHED |
| Object | Russian forces in 2008 |
—
|
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: Russian forces in 2008 | Statement: [Gori, wasOccupiedBy, Russian forces in 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasOccupiedBy Context triple: [Gori, wasOccupiedBy, Russian forces in 2008]
-
A.
firstOccupiedBy
Indicates which entity was the initial or earliest known occupant of a given place, position, or resource.
-
B.
occupiedBy
Indicates that a space, position, or role is currently being used, held, or filled by a particular entity.
-
C.
historicallyInhabitedBy
Indicates that a place or region was inhabited by a particular group or population during some period in the past.
-
D.
occupyingPower
chosen
Indicates that one entity holds military or political control over a territory that it does not legally own, typically as an occupying authority.
-
E.
countryOccupied
Indicates that one country has taken control of and is occupying the territory of another country, typically through military or coercive means.
- 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_69a24c8150408190910a693eb51c1f71 |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a250e401288190ba12322c9c5f07c9 |
completed | Feb. 28, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69a24eb59e808190811c20518f39b1cc |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.