Triple
T8493645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norby |
E201037
|
entity |
| Predicate | hasIntelligenceType |
P18468
|
FINISHED |
| Object | artificial intelligence |
—
|
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: artificial intelligence | Statement: [Norby, hasIntelligenceType, artificial intelligence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIntelligenceType Context triple: [Norby, hasIntelligenceType, artificial intelligence]
-
A.
typeOfIntelligence
chosen
Indicates that one entity is a specific kind or category of intelligence in relation to another entity.
-
B.
usesIntelligence
Indicates that an entity applies mental abilities such as reasoning, problem-solving, or understanding to perform an action or achieve a goal.
-
C.
providesIntelligenceTo
Indicates that one entity supplies information, analysis, or insight that enhances the knowledge or decision-making capability of another entity.
-
D.
hasCognitiveComponent
Indicates that the related entity or process involves or depends on mental activities such as thinking, reasoning, perception, or understanding.
-
E.
hasAI
Indicates that one entity possesses, incorporates, or is equipped with an artificial intelligence system.
- 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_69ca831ee390819095fae73400bbfafc |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe579b7088190b297b04527e36a2b |
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, 6:13 p.m.