Triple
T52981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ordinary People |
E1040
|
entity |
| Predicate | vocalFocus |
P2000
|
FINISHED |
| Object | lead vocal performance by John Legend |
—
|
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: lead vocal performance by John Legend | Statement: [Ordinary People, vocalFocus, lead vocal performance by John Legend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vocalFocus Context triple: [Ordinary People, vocalFocus, lead vocal performance by John Legend]
-
A.
vocalization
Indicates the act or manner of producing sounds or calls, typically as a means of communication.
-
B.
vocalRange
Indicates the span of pitches or notes that an entity (such as a singer or instrument) is capable of producing.
-
C.
voiceType
chosen
Indicates the specific vocal style, quality, or role associated with an entity’s voice in a given context.
-
D.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
E.
hasChorus
Indicates that something (typically a song or musical piece) includes a chorus section as part of its structure.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c709c248190bcd442c8d508e48c |
completed | Feb. 28, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69a24ac3c8dc819099849023bdaa35a9 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.