Triple
T14376376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | O2 mobile network |
E356484
|
entity |
| Predicate | usesRadioSpectrum |
P92788
|
FINISHED |
| Object | licensed mobile spectrum in the UK |
—
|
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: licensed mobile spectrum in the UK | Statement: [O2 mobile network, usesRadioSpectrum, licensed mobile spectrum in the UK]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesRadioSpectrum Context triple: [O2 mobile network, usesRadioSpectrum, licensed mobile spectrum in the UK]
-
A.
operatedInSpectrum
chosen
Indicates that an entity functioned or carried out its operations within a specified portion or range of the electromagnetic spectrum.
-
B.
usedInRadioBroadcasts
Indicates that something is employed or featured as part of radio broadcasts.
-
C.
frequencyBand
Indicates the specific range of frequencies within which a signal, measurement, or phenomenon is defined or operates.
-
D.
hasRadio
Indicates that an entity is equipped with or includes a radio device.
-
E.
usesFrequencyReuse
Indicates that one entity applies the technique of reusing the same frequency channels across different locations or cells within a system or network.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900949fc81909be0da1734c46645 |
completed | April 14, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69de2a9cb3e081909f6b33fdd939bb9e |
completed | April 14, 2026, 11:53 a.m. |
Created at: April 10, 2026, 1:16 a.m.