Triple
T29185795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephen Byerley |
E739864
|
entity |
| Predicate | testForHumanity |
P40583
|
FINISHED |
| Object | public appearance eating an apple |
—
|
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: public appearance eating an apple | Statement: [Stephen Byerley, testForHumanity, public appearance eating an apple]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testForHumanity Context triple: [Stephen Byerley, testForHumanity, public appearance eating an apple]
-
A.
test
Indicates that an entity performs, undergoes, or is associated with a testing or examination process involving another entity or condition.
-
B.
testingAuthority
Indicates that an entity has the official role or responsibility of conducting, overseeing, or validating a test or examination for another entity or process.
-
C.
testedFor
chosen
Indicates that an entity has been examined or analyzed to determine the presence, absence, or level of another specified entity or condition.
-
D.
testType
Indicates the specific category or kind of test associated with an entity or event.
-
E.
tests
Indicates that one entity examines, evaluates, or checks another entity or condition to determine its properties, performance, or correctness.
- 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_69f07cb74c2c8190ad396487fcb4fde6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6638722fc819098f18314dfa88a6c |
completed | May 2, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:59 a.m.