Triple
T4093926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IAS machine |
E87767
|
entity |
| Predicate | instructionFormat |
P37198
|
FINISHED |
| Object | two instructions per word |
—
|
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: two instructions per word | Statement: [IAS machine, instructionFormat, two instructions per word]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: instructionFormat Context triple: [IAS machine, instructionFormat, two instructions per word]
-
A.
commandInputFormat
chosen
Indicates the expected structure or syntax that a command must follow when being provided as input.
-
B.
instructionSetType
Indicates the type or category of an instruction set associated with a processor or computing architecture.
-
C.
instructionLength
Indicates the duration or amount of time required to carry out a given instruction or operation.
-
D.
instructionLevel
Indicates the degree or stage of guidance, teaching, or educational complexity associated with an action or relationship.
-
E.
instruction
Indicates that one entity provides a directive or order specifying an action that another entity should perform.
- 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_69aed94425148190be337845d56fac22 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcda2f408190bcf2b64535193162 |
completed | March 9, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69aef909c9c88190b09d48dad325a83c |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:40 p.m.