Triple
T24840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De Forest Phonofilm Corporation |
E495
|
entity |
| Predicate | technologyType |
P1482
|
FINISHED |
| Object | optical sound-on-film system |
—
|
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: optical sound-on-film system | Statement: [De Forest Phonofilm Corporation, technologyType, optical sound-on-film system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: technologyType Context triple: [De Forest Phonofilm Corporation, technologyType, optical sound-on-film system]
-
A.
technologyParadigm
Indicates a relationship where one entity represents or defines the overarching technological model, framework, or approach within which another entity operates or is categorized.
-
B.
platforms
Indicates that one entity provides or serves as a base, medium, or environment that supports the operation, distribution, or presentation of another entity.
-
C.
typeOfSupport
Indicates the kind or category of assistance, help, or backing provided in a given context.
-
D.
typeOfWork
Indicates the kind or category of work associated with or performed by an entity.
-
E.
computes
Indicates that one entity performs a calculation or processing operation to produce a result from given data or inputs.
- F. None of above. chosen
Provenance (4 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_69a243b4ac2c8190b93c303df797b7b2 |
completed | Feb. 28, 2026, 1:24 a.m. |
| NER | Named-entity recognition | batch_69a246d794448190bb2844fcd0538eaa |
completed | Feb. 28, 2026, 1:37 a.m. |
| PD | Predicate disambiguation | batch_69a24657635881908f3415bc1bdfa1b5 |
completed | Feb. 28, 2026, 1:35 a.m. |
| PDg | Predicate description generation | batch_69a246d6aca88190a86b7c41d497bacd |
completed | Feb. 28, 2026, 1:37 a.m. |
Created at: Feb. 28, 2026, 1:34 a.m.