Triple
T19190090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GPT-1 |
E469810
|
entity |
| Predicate | parameterCountCategory |
P4426
|
FINISHED |
| Object | hundreds of millions of parameters |
—
|
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: hundreds of millions of parameters | Statement: [GPT-1, parameterCountCategory, hundreds of millions of parameters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parameterCountCategory Context triple: [GPT-1, parameterCountCategory, hundreds of millions of parameters]
-
A.
parameterCount
Indicates the number of parameters associated with a given function, method, or callable entity.
-
B.
parameterCountRelativeTo
Indicates a relationship comparing the number of parameters of one entity (such as a function, method, or operation) to that of another entity.
-
C.
hasCategoryCount
Indicates the number of distinct categories associated with a given entity.
-
D.
numberOfCounts
Indicates the total quantity or tally of discrete occurrences, items, or instances associated with an entity or event.
-
E.
hasNumberCategory
chosen
Indicates that an entity is associated with a specific numerical classification or type.
- 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f8a16e20819080baa5112f000b41 |
completed | April 20, 2026, 9:57 a.m. |
| PD | Predicate disambiguation | batch_69e4b9bb158481909478ca2e06f3ba39 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:07 p.m.