Triple
T8502292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CSMA |
E201247
|
entity |
| Predicate | originField |
P58693
|
FINISHED |
| Object | computer networking |
—
|
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: computer networking | Statement: [CSMA, originField, computer networking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originField Context triple: [CSMA, originField, computer networking]
-
A.
formerField
Indicates that an entity previously had a particular field, role, or area of activity, but no longer does.
-
B.
originUse
Indicates that one entity is used as the original source, basis, or starting point for the creation, derivation, or use of another entity.
-
C.
fromField
chosen
Indicates that something originates in, is sourced from, or is associated with a particular field or domain.
-
D.
primaryField
Indicates the main area of focus, discipline, or domain most centrally associated with an entity.
-
E.
overField
Indicates a spatial relationship where one entity is positioned above or extends across the area of a field.
- 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_69ca831fe47c8190b5c57b456d2aefa0 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe59c413881909513d8a9d52333c0 |
completed | March 31, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69cbd10a4b0881909e254117780dc823 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:14 p.m.