Triple
T33699285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SI-112 (Municipality of Sevnica) |
E863408
|
entity |
| Predicate | hasCountryPrefix |
P147380
|
FINISHED |
| Object | SI |
—
|
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: SI | Statement: [SI-112 (Municipality of Sevnica), hasCountryPrefix, SI]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCountryPrefix Context triple: [SI-112 (Municipality of Sevnica), hasCountryPrefix, SI]
-
A.
hasNumberInCountry
Indicates that an entity possesses or is assigned a specific phone or identification number within a particular country.
-
B.
associatedCountryCodePrefix
chosen
Indicates that one entity has a country code prefix that is associated with, or corresponds to, the other entity.
-
C.
internationalPrefix
Indicates that one entity is the international dialing prefix used to place telephone calls from the other entity’s country to foreign destinations.
-
D.
isCountryCode
Indicates that one entity is a valid country code designating the country represented by the other entity.
-
E.
mobileNumberPrefix
Indicates that one entity is a telephone number prefix associated with, or used to begin, the other entity’s mobile phone numbers.
- 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_69f3498723a08190ac034339cc78eade |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037e0953908190b2930b3c06a40129 |
completed | May 12, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_6a0379f6c3308190b954f7810214ceed |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:43 a.m.