Triple
T2159610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halo (song) |
E47969
|
entity |
| Predicate | vocalRangeDescription |
P24750
|
FINISHED |
| Object | showcases Beyoncé’s upper register |
—
|
LITERAL 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: showcases Beyoncé’s upper register | Statement: [Halo (song), vocalRangeDescription, showcases Beyoncé’s upper register]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vocalRangeDescription Context triple: [Halo (song), vocalRangeDescription, showcases Beyoncé’s upper register]
-
A.
vocalRange
Indicates the span of pitches or notes that an entity (such as a singer or instrument) is capable of producing.
-
B.
hasVocalRangeDescription
chosen
Indicates that an entity is associated with a textual description of its vocal range or vocal capabilities.
-
C.
vocalForces
Indicates a relationship where one entity uses vocal expression (such as speech, singing, or sound) to exert influence, pressure, or compulsion on another entity.
-
D.
voiceType
Indicates the specific vocal style, quality, or role associated with an entity’s voice in a given context.
-
E.
featuresVocalist
Indicates that one entity (such as a song, track, or performance) includes another entity serving as a vocalist or featured singer.
- 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_69a88a1d1fd8819088b34990d69a712f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe8894d481908eda9363fd36fea6 |
completed | March 7, 2026, 5:58 a.m. |
| PD | Predicate disambiguation | batch_69abbd9c90408190b6b65498ca43ce26 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.