Triple
T32532831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hungary–Serbia border |
E831509
|
entity |
| Predicate | non_EU_side_country |
P167902
|
FINISHED |
| Object | Serbia |
—
|
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: Serbia | Statement: [Hungary–Serbia border, non_EU_side_country, Serbia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: non_EU_side_country Context triple: [Hungary–Serbia border, non_EU_side_country, Serbia]
-
A.
nonEUCountryOnOneSide
chosen
Indicates that at least one party or side involved in the relationship is a country that is not a member of the European Union.
-
B.
majorNonNATOAlly
Indicates that one entity has designated the other as a major non-NATO ally, granting it a special security and defense cooperation status outside the NATO alliance.
-
C.
nationalSideOf
Indicates that one entity is the national team or national representative side associated with another entity, such as a country or nation.
-
D.
nonParticipatingMemberStates
Indicates that certain member states are part of an organization or agreement but do not take part in a specified activity, process, or decision.
-
E.
regionCountrySide
Indicates that a region is located in or associated with the countryside or rural area of a country.
- 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_69f34924b1cc8190ad3aca0c0f012a7e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c568ae488190aa7c3bb8d65a655a |
completed | May 3, 2026, 3:47 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1:01 a.m.