Triple
T9870273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PowerPC G5 |
E239937
|
entity |
| Predicate | endianMode |
P11220
|
FINISHED |
| Object | big-endian |
—
|
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: big-endian | Statement: [PowerPC G5, endianMode, big-endian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endianMode Context triple: [PowerPC G5, endianMode, big-endian]
-
A.
endianess
Indicates the byte order relationship specifying how multi-byte data is arranged in memory or during transmission (e.g., little-endian vs big-endian).
-
B.
endianness
chosen
Indicates the ordering of bytes used to represent multi-byte data values in memory or storage.
-
C.
bitOrder
Indicates the ordering or sequence of bits within a binary representation, such as which bit positions are considered first or most significant.
-
D.
isEndiannessAgnostic
Indicates that the behavior or data format is independent of byte order, producing correct results regardless of the system’s endianness.
-
E.
alternateMode
Indicates that one entity functions as an alternative form, configuration, or mode of operation for 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_69ca84e7506c819095cbde4ff16512bb |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3d62628819094786a49b9bcd09b |
completed | April 2, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:36 p.m.