Triple
T22489167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chai |
E555968
|
entity |
| Predicate | supportsAssertionType |
P24486
|
FINISHED |
| Object | equality assertions |
—
|
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: equality assertions | Statement: [Chai, supportsAssertionType, equality assertions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsAssertionType Context triple: [Chai, supportsAssertionType, equality assertions]
-
A.
supportsAssertionLibraries
Indicates that one entity provides compatibility with or functionality for using specific assertion libraries in conjunction with another entity.
-
B.
supportsType
chosen
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
C.
supportsTargetType
Indicates that one entity is capable of operating with, handling, or being compatible with a specified target type.
-
D.
supportsTestType
Indicates that one entity is capable of handling, executing, or being compatible with a specified type of test.
-
E.
typicalAssertionLibrary
Indicates that one entity is a standard or commonly used collection of assertions or checks applied within the context of another entity (such as a test, framework, or 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c3f3b4c819092bfe6495c61db46 |
completed | April 29, 2026, 1:17 a.m. |
| PD | Predicate disambiguation | batch_69e898b6eee08190ba673a0ee329e671 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:49 p.m.