Triple
T6108711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abyssinian maid |
E136177
|
entity |
| Predicate | inspires |
P63928
|
FINISHED |
| Object | speaker of Kubla Khan |
—
|
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: speaker of Kubla Khan | Statement: [Abyssinian maid, inspires, speaker of Kubla Khan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inspires Context triple: [Abyssinian maid, inspires, speaker of Kubla Khan]
-
A.
inspiration
Indicates that one entity serves as a motivating or creative influence that stimulates ideas, actions, or feelings in another entity.
-
B.
hasInspired
chosen
Indicates that one entity has served as a source of motivation, creativity, or influence leading to ideas, actions, or works in another entity.
-
C.
inspiredField
Indicates that one entity served as a source of inspiration or influence for the development, direction, or characteristics of a particular field or domain.
-
D.
inspirationConcept
Indicates that one concept serves as a source of inspiration or creative influence for another concept.
-
E.
inspiredAuthor
Indicates that one entity served as a source of creative or intellectual inspiration for an author 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_69c0089ea6f88190b349be53e04b4f5f |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05b835ed48190971c3ba397ca329f |
completed | March 22, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69c049f80e2081909b7d84a104cda68d |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:13 p.m.