Triple
T10536838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mabel Williams |
E248587
|
entity |
| Predicate | inspiredByUseOf |
P24441
|
FINISHED |
| Object | homemade cosmetics |
—
|
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: homemade cosmetics | Statement: [Mabel Williams, inspiredByUseOf, homemade cosmetics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inspiredByUseOf Context triple: [Mabel Williams, inspiredByUseOf, homemade cosmetics]
-
A.
inspiredByOrRelatedTo
Indicates that one entity draws inspiration from, is influenced by, or is otherwise thematically or conceptually connected to another entity.
-
B.
partlyInspiredBy
Indicates that one entity has been influenced to some extent, but not wholly, by another entity in its creation, development, or form.
-
C.
inspiredDevelopmentOf
Indicates that one entity served as a motivating influence or creative stimulus leading to the development or creation of another entity.
-
D.
wasUsedBy
chosen
Indicates that something served as a tool, resource, or means for an agent to perform an action or achieve a result.
-
E.
inspiredByPhrase
Indicates that one entity’s creation, idea, or expression is motivated or shaped by the content or wording of a particular phrase.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a554fb4819081e9618bab051dc6 |
completed | April 7, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69d4fb9729288190a0149f127acd7ae3 |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:31 p.m.