Triple
T21004596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | E minor |
E517381
|
entity |
| Predicate | relativeKeyOf |
P142442
|
FINISHED |
| Object | G major |
—
|
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: G major | Statement: [E minor, relativeKeyOf, G major]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeKeyOf Context triple: [E minor, relativeKeyOf, G major]
-
A.
keyRelation
Indicates a functional or defining association where one entity serves as a key or primary reference for accessing, identifying, or organizing another entity.
-
B.
keyOf
Indicates that one entity functions as the key (identifier or access token) associated with another entity.
-
C.
associatedKeyOfCollection
Indicates a relationship where a key is linked or bound to a specific collection, typically identifying or indexing that collection within a broader context.
-
D.
relativeAlias
Indicates that one entity is known or referred to by an alternative name or label that is contextually related to another entity.
-
E.
relativePosition
Indicates the spatial relationship of one entity’s location with respect to another entity’s position.
- F. None of above. chosen
Provenance (4 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_69e0b50192308190a284fcc89dd23a49 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc3b25ec8190aa4530d1f0bb2b9e |
completed | April 21, 2026, 4:25 a.m. |
| PD | Predicate disambiguation | batch_69e5dbec80708190a49bccab7ff97e7b |
completed | April 20, 2026, 7:55 a.m. |
| PDg | Predicate description generation | batch_69e5e2df1a888190b5b478e76bdf7fdf |
completed | April 20, 2026, 8:25 a.m. |
Created at: April 16, 2026, 1:52 p.m.