Triple
T36838962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magyar Telekom |
E910349
|
entity |
| Predicate | telephonyPrefix |
P182088
|
FINISHED |
| Object | +36 30 (mobile number range) |
—
|
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: +36 30 (mobile number range) | Statement: [Magyar Telekom, telephonyPrefix, +36 30 (mobile number range)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: telephonyPrefix Context triple: [Magyar Telekom, telephonyPrefix, +36 30 (mobile number range)]
-
A.
nationalPrefixForDomesticCalls
Indicates the dialing prefix that must be used when making domestic telephone calls within a given country or numbering plan.
-
B.
mobileNumberPrefix
chosen
Indicates that one entity is a telephone number prefix associated with, or used to begin, the other entity’s mobile phone numbers.
-
C.
tollFreePrefixExample
Indicates that the subject is an example of a telephone number prefix that designates a toll-free calling number.
-
D.
internationalPrefix
Indicates that one entity is the international dialing prefix used to place telephone calls from the other entity’s country to foreign destinations.
-
E.
callingCode
Indicates the telephone country or area code associated with an entity for making phone calls.
- 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.