Triple
T28406563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | INT 10h video services |
E719543
|
entity |
| Predicate | registerUsedForFunctionSelection |
P64049
|
FINISHED |
| Object | AH |
—
|
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: AH | Statement: [INT 10h video services, registerUsedForFunctionSelection, AH]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: registerUsedForFunctionSelection Context triple: [INT 10h video services, registerUsedForFunctionSelection, AH]
-
A.
usesFunction
Indicates that one entity employs, invokes, or relies on a particular function to perform an operation or achieve a result.
-
B.
usedToSelect
chosen
Indicates that one entity serves as a criterion, tool, or basis for choosing or determining another entity.
-
C.
hasUsageRegister
Indicates that a linguistic expression is associated with a particular usage register or level of formality in communication.
-
D.
exportUse
Indicates that something is used, intended, or suitable for export from one place or market to another.
-
E.
registersUsed
Indicates that certain registers are utilized or occupied by a given operation, instruction, or computational 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_69eff6f0f37c8190b37bc6fab08a9449 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a931748190a637e631a52bbfaa |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 1:23 a.m.