Triple
T17806039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | G.726 |
E444560
|
entity |
| Predicate | usesCodingMethod |
P33646
|
FINISHED |
| Object | adaptive differential pulse-code modulation |
—
|
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: adaptive differential pulse-code modulation | Statement: [G.726, usesCodingMethod, adaptive differential pulse-code modulation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCodingMethod Context triple: [G.726, usesCodingMethod, adaptive differential pulse-code modulation]
-
A.
programmingMethod
Indicates the method, technique, or approach used to carry out a programming-related activity or task.
-
B.
usesCodeName
Indicates that one entity refers to another entity by a code name or alias instead of its real or full designation.
-
C.
usesMethods
chosen
Indicates that one entity employs, applies, or relies on specific methods or techniques to perform an action or achieve a result.
-
D.
usesCodeOfPoints
Indicates that one entity evaluates or governs something according to the rules and scoring system defined by another entity’s code of points.
-
E.
codeFor
Indicates that one entity serves as the implementation, encoding, or programmatic representation for another entity.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4880385b48190b8dea0f05dfa1300 |
completed | April 19, 2026, 7:45 a.m. |
| PD | Predicate disambiguation | batch_69e3d8de28688190844b65acf6af54e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:14 a.m.