Triple
T23387466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UCS-2 |
E593922
|
entity |
| Predicate | usesByteOrder |
P11220
|
FINISHED |
| Object | big-endian or little-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 or little-endian | Statement: [UCS-2, usesByteOrder, big-endian or little-endian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesByteOrder Context triple: [UCS-2, usesByteOrder, big-endian or little-endian]
-
A.
endiannessDependent
Indicates that the relationship or behavior varies depending on the byte-order (endianness) used to represent multi-byte data.
-
B.
endianness
chosen
Indicates the ordering of bytes used to represent multi-byte data values in memory or storage.
-
C.
usesByteOrderMark
Indicates that a text or data stream includes a byte order mark (BOM) to specify its encoding or endianness.
-
D.
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).
-
E.
isEndiannessAgnostic
Indicates that the behavior or data format is independent of byte order, producing correct results regardless of the system’s endianness.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a498fd08819085e90a872d9d0c7a |
completed | April 29, 2026, 6:26 a.m. |
| PD | Predicate disambiguation | batch_69f061dde2e481908308952f9c0d3c2e |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:35 p.m.