Triple
T33203024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hymn to the Sea |
E849955
|
entity |
| Predicate | basedOnMotifFrom |
P31989
|
FINISHED |
| Object | My Heart Will Go On |
—
|
NE NERFINISHED |
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: My Heart Will Go On | Statement: [Hymn to the Sea, basedOnMotifFrom, My Heart Will Go On]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnMotifFrom Context triple: [Hymn to the Sea, basedOnMotifFrom, My Heart Will Go On]
-
A.
usesMotifsFrom
chosen
Indicates that one entity incorporates or draws upon recurring themes, patterns, or elements that originate from another entity.
-
B.
featuresMotif
Indicates that something contains, incorporates, or prominently includes a particular recurring motif or pattern.
-
C.
transformationMotif
Indicates a recurring pattern or theme in which one entity undergoes a change in form, state, or identity in relation to another.
-
D.
hasTypeOfMotif
Indicates that one entity features or is characterized by a specific kind or category of motif.
-
E.
numberOfMotifs
Indicates the count of distinct motifs associated with or contained within a given 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_69f3495efedc8190843a5728089544b9 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
Created at: May 1, 2026, 1:30 a.m.