Triple
T23499171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple |
E571791
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Heartshine |
—
|
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: Heartshine | Statement: [Apple, hasPart, Heartshine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heartshine Context triple: [Apple, hasPart, Heartshine]
-
A.
Heartshine
chosen
Heartshine is a song by the American rock band Mother Love Bone from their album "Apple," showcasing their blend of glam-influenced hard rock and grunge.
-
B.
Soulshine
"Soulshine" is a soulful, blues-infused rock song by The Allman Brothers Band, widely cherished for its uplifting lyrics and emotive guitar work.
-
C.
Spirit Shine
Spirit Shine is a song by the American punk rock band The Gray Race.
-
D.
Shining Through
Shining Through is a 1992 World War II romantic thriller film starring Michael Douglas and Melanie Griffith, centered on an American woman who becomes a spy behind enemy lines in Nazi Germany.
-
E.
Starlight
Starlight is a fictional character or element associated with the Evolver universe, likely representing a key component or aspect within that setting.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b4829881909b77a70e942bbd54 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a8fb71c08190a30500b3f63a9ce6 |
completed | April 29, 2026, 6:45 a.m. |
Created at: April 17, 2026, 6:06 p.m.