Triple
T26672538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croatia–Bosnia and Herzegovina border |
E672371
|
entity |
| Predicate | languageUsedAlongBorder |
P77518
|
FINISHED |
| Object | Croatian |
—
|
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: Croatian | Statement: [Croatia–Bosnia and Herzegovina border, languageUsedAlongBorder, Croatian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageUsedAlongBorder Context triple: [Croatia–Bosnia and Herzegovina border, languageUsedAlongBorder, Croatian]
-
A.
languageAlongBorder
chosen
Indicates that a particular language is spoken or prevalent along the border between two regions or entities.
-
B.
countryBorderType
Indicates the type or nature of the border relationship that exists between two countries.
-
C.
countryBordering
Indicates that one country shares a land or maritime boundary directly with another country.
-
D.
provinceBordering
Indicates that two provinces share a common boundary or border with each other.
-
E.
borderDialectOf
Indicates a dialect that is spoken in a border area and is linguistically associated with or derived from a particular neighboring language or dialect.
- 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_69eecda00a9c8190b2691f4d89db03b6 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69fbaebc8f2c8190b94f1b4a3ec92e8c |
completed | May 6, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
Created at: April 27, 2026, 3:13 a.m.