Triple
T33029514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Relay |
E845124
|
entity |
| Predicate | concurrentTechnologies |
P171624
|
FINISHED |
| Object | Usenet |
—
|
NE NERFINISHED |
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: Usenet | Statement: [Relay, concurrentTechnologies, Usenet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: concurrentTechnologies Context triple: [Relay, concurrentTechnologies, Usenet]
-
A.
combinesTechnologyFrom
Indicates that one entity integrates or merges technological components, methods, or features originating from another entity.
-
B.
laterUsedTechnology
Indicates that one entity adopted or employed a technology after another entity had already used it.
-
C.
curdTechnology
Indicates a relationship where a particular technology is used in, enables, or characterizes the process of making or handling curd.
-
D.
opposedTechnology
Indicates that one entity actively resists, rejects, or works against the use, adoption, or development of a particular technology associated with another entity.
-
E.
technologyCounterpartOf
chosen
Indicates a relationship where one technology serves as an equivalent, alternative, or corresponding counterpart to another technology.
- 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_69f34950749c8190ae05cd27adb16d58 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:24 a.m.