Triple
T8985458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Denise |
E214650
|
entity |
| Predicate | outputTo |
P84816
|
FINISHED |
| Object | analog RGB video signals |
—
|
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: analog RGB video signals | Statement: [Denise, outputTo, analog RGB video signals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outputTo Context triple: [Denise, outputTo, analog RGB video signals]
-
A.
outputsTo
chosen
Indicates that the result or data produced by one entity is directed or sent to another entity as its destination or target.
-
B.
outputOf
Indicates that one entity is the result or product generated by the processing, operation, or behavior of another entity.
-
C.
outputProperty
Indicates that a property or attribute is produced, exposed, or yielded as the output of a process, function, or system.
-
D.
compositeOutputStandard
Indicates that the entity conforms to or is produced according to a specified composite output standard that defines how multiple outputs are structured or combined.
-
E.
outputFunction
Indicates that one entity serves as the function or procedure responsible for producing or returning the output of another entity or process.
- 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_69ca839f76bc8190a4b7123cdd682199 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67eddbf08190afca16e0be435241 |
completed | April 1, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69cc5edba0f88190b97401636a076d7a |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:03 p.m.