Triple
T33173437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amiga 500 Plus |
E849096
|
entity |
| Predicate | serialPort |
P85938
|
FINISHED |
| Object | RS-232 serial port |
—
|
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: RS-232 serial port | Statement: [Amiga 500 Plus, serialPort, RS-232 serial port]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serialPort Context triple: [Amiga 500 Plus, serialPort, RS-232 serial port]
-
A.
serialInterface
Indicates a relationship where data is transmitted between components over a serial communication interface (one bit at a time over a communication line or bus).
-
B.
serialProperty
Indicates that one entity is a property or attribute that is part of a sequential or ordered series associated with another entity.
-
C.
hasSerialPort
chosen
Indicates that an entity is equipped with or includes a serial port interface.
-
D.
serialStudio
Indicates a relationship where an entity is associated with a studio in a serial or recurring production context (e.g., a studio responsible for a series or multiple installments).
-
E.
bitSerialOrParallel
Indicates whether a bit-level operation or data transfer is performed in serial form (one bit at a time) or in parallel form (multiple bits simultaneously).
- 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_69f3495be8808190bbf427733df08aad |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6e02ba6b881908dfafc52d3b75f1c |
completed | May 3, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69f6de09c2f481909f8b2545d3208c9f |
completed | May 3, 2026, 5:32 a.m. |
Created at: May 1, 2026, 1:29 a.m.