Triple
T3542965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ResNet |
E74928
|
entity |
| Predicate | hasArchitectureDepth |
P36777
|
FINISHED |
| Object | 18 layers |
—
|
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: 18 layers | Statement: [ResNet, hasArchitectureDepth, 18 layers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArchitectureDepth Context triple: [ResNet, hasArchitectureDepth, 18 layers]
-
A.
hasDepth
chosen
Indicates that an entity possesses a measurable extent or distance from its surface inward or from top to bottom.
-
B.
hasAverageDepth
Indicates that an entity possesses a specified mean depth value, typically measured over its entire extent or area.
-
C.
hasApproximateDepth
Indicates that an entity is associated with a depth value that is not exact but estimated or approximate.
-
D.
hasSubArchitecture
Indicates that one architectural component or structure is a subordinate or constituent part of a larger overarching architecture.
-
E.
usesArchitecture
Indicates that one entity is built, implemented, or operates according to the architectural style, framework, or design specified by 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_69ad85d274cc8190ab59c97298a1cfbf |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbf752dd481909226044ffe595338 |
completed | March 8, 2026, 6:27 p.m. |
| PD | Predicate disambiguation | batch_69adae15749881909b847c6ca73c934e |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:20 p.m.