Triple
T17702300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shirley Douglas |
E441336
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Wind at My Back |
E1007878
|
NE 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: Wind at My Back | Statement: [Shirley Douglas, notableWork, Wind at My Back]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wind at My Back Context triple: [Shirley Douglas, notableWork, Wind at My Back]
-
A.
Wind at My Back
chosen
Wind at My Back is a Canadian television drama series set during the Great Depression, following the struggles and relationships of a small-town family.
-
B.
To the Wind
"To the Wind" is a song by the metalcore band For the Fallen Dreams from their album "Changes."
-
C.
The Wind and I
"The Wind and I" is a musical piece or movement likely characterized by a lyrical, atmospheric style that evokes the motion and feeling of wind.
-
D.
Me and the Wind
"Me and the Wind" is a track by the British rock band Mummer, known for its atmospheric, introspective style.
-
E.
Something in the Wind
"Something in the Wind" is a 1947 American musical comedy film starring Deanna Durbin, known for its lighthearted romance, mistaken-identity plot, and lively musical numbers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4715c3980819094b080a871df1100 |
completed | April 19, 2026, 6:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02301ef8488190a71d06780a4f6b29 |
completed | May 11, 2026, 7:38 p.m. |
Created at: April 10, 2026, 10:05 a.m.