Triple
T30279030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latvia–Estonia border |
E770033
|
entity |
| Predicate | separatesStates |
P50632
|
FINISHED |
| Object | Republic of Latvia |
—
|
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: Republic of Latvia | Statement: [Latvia–Estonia border, separatesStates, Republic of Latvia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: separatesStates Context triple: [Latvia–Estonia border, separatesStates, Republic of Latvia]
-
A.
separatesState
chosen
Indicates that one entity serves as a dividing boundary or barrier between two distinct states or regions.
-
B.
dividedStatesInto
Indicates that one entity partitioned another entity into multiple distinct states or regions.
-
C.
states
Indicates that an entity formally declares, expresses, or asserts a fact, opinion, or condition about another entity or situation.
-
D.
separatesNeighborhoodFromState
Indicates that something serves as a boundary or dividing feature between a neighborhood and the larger state it is part of.
-
E.
primaryStates
Indicates that certain states or conditions are the main or most fundamental ones within a given context or system.
- 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_69f224868fa8819099127eaf8855a28f |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 7:45 p.m.