Triple
T2334663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Ossetia |
E44281
|
entity |
| Predicate | consideredByMostStatesAs |
P38283
|
FINISHED |
| Object | part of Georgia |
—
|
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: part of Georgia | Statement: [South Ossetia, consideredByMostStatesAs, part of Georgia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consideredByMostStatesAs Context triple: [South Ossetia, consideredByMostStatesAs, part of Georgia]
-
A.
majorState
Indicates that a state holds significant power, influence, or importance relative to other states within a given system or context.
-
B.
primaryStates
Indicates that certain states or conditions are the main or most fundamental ones within a given context or system.
-
C.
representedState
Indicates that one entity serves as a representation or depiction of the state or condition of another entity.
-
D.
respondentState
Indicates the state or jurisdiction in which the respondent is located, resides, or is legally associated.
-
E.
states
Indicates that an entity formally declares, expresses, or asserts a fact, opinion, or condition about another entity or situation.
- F. None of above. chosen
Provenance (4 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_69a889132b488190bbb43ad4780ddd92 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abc6f75d888190a2e41edaa532e83f |
completed | March 7, 2026, 6:34 a.m. |
| PD | Predicate disambiguation | batch_69abc594087c819098100a10c5478a4b |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc6f4245881909282b3184a288e2a |
completed | March 7, 2026, 6:34 a.m. |
Created at: March 4, 2026, 7:51 p.m.