Triple
T21191975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TD-SCDMA |
E522232
|
entity |
| Predicate | usesDuplexingMethod |
P85772
|
FINISHED |
| Object | time-division duplexing |
—
|
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: time-division duplexing | Statement: [TD-SCDMA, usesDuplexingMethod, time-division duplexing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDuplexingMethod Context triple: [TD-SCDMA, usesDuplexingMethod, time-division duplexing]
-
A.
usesDuplexMethod
chosen
Indicates that one entity employs a duplex method, meaning a two-way or bidirectional technique or process, in relation to another entity or context.
-
B.
duplexModeInOriginalSpec
Indicates that the duplex (two-sided operation) mode is defined according to the original specification.
-
C.
duplexMode
Indicates whether a communication link or device operates in half-duplex or full-duplex mode, defining if data can flow in one or both directions simultaneously.
-
D.
laterSupportedDuplexMode
Indicates that one entity provided support for duplex mode at a later time than another entity.
-
E.
hasDuplexTunnel
Indicates that there exists a bidirectional (two-way) tunnel connection between two entities.
- 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_69e0b51061388190aa03f19700d3ef04 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e733381f288190b3da795f62a39568 |
completed | April 21, 2026, 8:20 a.m. |
| PD | Predicate disambiguation | batch_69e5f6027c248190a170a36612bd337e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:07 p.m.