Triple
T3175171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theme from "My Favorite Things" (revised) |
E66445
|
entity |
| Predicate | isDerivativeOf |
P15288
|
FINISHED |
| Object | original song "My Favorite Things" |
—
|
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: original song "My Favorite Things" | Statement: [Theme from "My Favorite Things" (revised), isDerivativeOf, original song "My Favorite Things"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDerivativeOf Context triple: [Theme from "My Favorite Things" (revised), isDerivativeOf, original song "My Favorite Things"]
-
A.
derivedFrom
Indicates that one entity originates, is obtained, or is developed from another source entity.
-
B.
differentiatedFrom
Indicates that one entity is distinguished or set apart from another by identifying differences between them.
-
C.
derivedBy
Indicates that one entity is obtained, produced, or inferred from another through some transformation, process, or reasoning.
-
D.
isVersionOf
chosen
Indicates that one entity is a particular version, edition, or variant derived from another entity.
-
E.
derivationType
Indicates the specific manner or process by which one entity is derived or obtained from another.
- 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada671e6848190a683eec1519b9268 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e02677c8190a21d93b1259b2761 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.