Triple
T36553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold Stephen Black |
E723
|
entity |
| Predicate | patentOn |
P74
|
FINISHED |
| Object | negative feedback amplifier |
—
|
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: negative feedback amplifier | Statement: [Harold Stephen Black, patentOn, negative feedback amplifier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patentOn Context triple: [Harold Stephen Black, patentOn, negative feedback amplifier]
-
A.
patent
chosen
Indicates that a legal protection has been granted to an entity for an invention, giving it exclusive rights to make, use, or sell that invention.
-
B.
patentDate
Indicates the date on which a patent was officially granted or registered.
-
C.
usedOn
Indicates that one entity is applied to, operated on, or otherwise utilized in relation to another entity.
-
D.
wasInventedBy
Indicates that something (typically an object, concept, or process) was created or brought into existence by a particular inventor or originator.
-
E.
isOn
Indicates that one entity is physically positioned above and in contact with the top surface of 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_69a247a8f6c08190bac804906d62ed5a |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24bb753f081909cd8b25cfb8e08af |
completed | Feb. 28, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69a24ab4a6908190b6f355415ffe7948 |
completed | Feb. 28, 2026, 1:53 a.m. |
Created at: Feb. 28, 2026, 1:46 a.m.