Triple
T13060315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blended Family |
E329177
|
entity |
| Predicate | chorusFocus |
P108250
|
FINISHED |
| Object | unity in a blended family |
—
|
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: unity in a blended family | Statement: [Blended Family, chorusFocus, unity in a blended family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chorusFocus Context triple: [Blended Family, chorusFocus, unity in a blended family]
-
A.
chorus
Indicates that multiple entities jointly produce or participate in a coordinated vocal or expressive performance, typically as a unified group.
-
B.
chorusFeature
Indicates that one entity participates in or is highlighted within the chorus section of another entity, such as a song or musical piece.
-
C.
chorusType
Indicates the specific kind or category of chorus associated with an entity (e.g., type of vocal ensemble or choral grouping).
-
D.
chorusDirector
Indicates that one entity serves as the director or leader of a chorus in relation to another entity.
-
E.
lyricFocus
Indicates that the primary emphasis or subject of the lyrics is centered on a particular entity or theme.
- 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_69d80771749c81909a6d9197b9504872 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d980e7ee548190b4b18bdb1357c359 |
completed | April 10, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69d9803d46688190bac6b7d208f08d01 |
completed | April 10, 2026, 10:57 p.m. |
| PDg | Predicate description generation | batch_69d980e622e8819087a69bfb1660dd64 |
completed | April 10, 2026, 10:59 p.m. |
Created at: April 9, 2026, 8:58 p.m.