Triple
T28923620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madonna: True Blue (music video) |
E733584
|
entity |
| Predicate | featuresLipSyncPerformance |
P198184
|
FINISHED |
| Object | True Blue (song) |
—
|
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: True Blue (song) | Statement: [Madonna: True Blue (music video), featuresLipSyncPerformance, True Blue (song)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresLipSyncPerformance Context triple: [Madonna: True Blue (music video), featuresLipSyncPerformance, True Blue (song)]
-
A.
featuresVocalHarmonyBy
Indicates that the subject work includes vocal harmony performances contributed by the specified artist or group.
-
B.
featuresFalsettoVocalsBy
Indicates that a musical work includes falsetto singing performed by the specified vocalist or vocal group.
-
C.
hasVocalPerformanceBy
Indicates that a vocal performance in a work or recording is performed by a specified person or group.
-
D.
featuresVocal
Indicates that one entity includes or presents the vocal performance or voice of another entity.
-
E.
providedVocalPerformanceFor
Indicates that one entity delivered or contributed a vocal performance in support of, or as part of, another entity’s work, event, or production.
- 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_69f05b0a5cc0819094828367ae204b70 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fed09a12648190affcd9bacf7ca275 |
completed | May 9, 2026, 6:13 a.m. |
| PD | Predicate disambiguation | batch_69fecf91d6f481908deb60c965c433ed |
completed | May 9, 2026, 6:09 a.m. |
| PDg | Predicate description generation | batch_69fed098328c819085979de6b179b378 |
completed | May 9, 2026, 6:13 a.m. |
Created at: April 28, 2026, 8:21 a.m.