Triple
T29071549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Kind of Magic |
E735823
|
entity |
| Predicate | featuresSongFrom |
P198848
|
FINISHED |
| Object | Highlander |
—
|
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: Highlander | Statement: [A Kind of Magic, featuresSongFrom, Highlander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresSongFrom Context triple: [A Kind of Magic, featuresSongFrom, Highlander]
-
A.
featuresSongwriter
Indicates that a musical work includes or credits a particular person as its songwriter.
-
B.
featuresReRecordedSong
Indicates that an entity (such as an album, release, or performance) includes a song that has been recorded again in a new version distinct from its original recording.
-
C.
featuresSongwriterCovered
Indicates that one entity includes or highlights a songwriter whose work has been covered in a song or performance by another entity.
-
D.
featuresNewSong
Indicates that an entity presents, includes, or showcases a newly released song.
-
E.
featuresIntrospectiveLyrics
Indicates that the subject contains lyrics characterized by self-reflection, inner thought, or personal emotional examination.
- 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_69f077e9b0a48190bb79548279cb7f64 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ff0e9c75208190a4423261f00b79b3 |
completed | May 9, 2026, 10:38 a.m. |
| PD | Predicate disambiguation | batch_69ff0e07f08481909c4ae322632a6bf0 |
completed | May 9, 2026, 10:35 a.m. |
| PDg | Predicate description generation | batch_69ff0e9b7acc81909a0ee66201a06877 |
completed | May 9, 2026, 10:38 a.m. |
Created at: April 28, 2026, 10:20 a.m.