Triple
T6222947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurzweil reading machine for the blind |
E139158
|
entity |
| Predicate | commercialRelease |
P785
|
FINISHED |
| Object | mid-1970s |
—
|
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: mid-1970s | Statement: [Kurzweil reading machine for the blind, commercialRelease, mid-1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commercialRelease Context triple: [Kurzweil reading machine for the blind, commercialRelease, mid-1970s]
-
A.
commercializedIn
Indicates that something has been brought to market or made available for commercial sale or use within a specified place or context.
-
B.
publicRelease
Indicates that something is made available to the general public, typically after any private or restricted access period has ended.
-
C.
commercialized
chosen
Indicates that something has been developed, marketed, or exploited for profit in a commercial context.
-
D.
commercialProduct
Indicates that one entity is a product or service offered for sale or commercial use by another entity.
-
E.
commercialAvailability
Indicates that an entity is offered for sale or otherwise obtainable through commercial channels.
- 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_69c008aecb0c81909984b48f733ce8ae |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062c06c7881909999ba44aa4a23f9 |
completed | March 22, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69c055ffdf54819086d987d646e44ff5 |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:22 p.m.