Triple
T3127751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Closed on Sunday |
E65336
|
entity |
| Predicate | lyricReference |
P45526
|
FINISHED |
| Object | protecting one’s 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: protecting one’s family | Statement: [Closed on Sunday, lyricReference, protecting one’s family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lyricReference Context triple: [Closed on Sunday, lyricReference, protecting one’s family]
-
A.
lyricFocus
Indicates that the primary emphasis or subject of the lyrics is centered on a particular entity or theme.
-
B.
lyricsBy
Indicates that the lyrics of a song or musical work were written or authored by a specified person or entity.
-
C.
lyricSetting
Indicates that one entity serves as the text or lyrics that are set to music or otherwise musically realized by another entity.
-
D.
hasLyric
Indicates that one entity (typically a musical work or track) contains or is associated with the lyrics provided by another entity.
-
E.
scriptUsedInLyrics
Indicates that a particular writing system or script is used to write or represent the lyrics of a song or musical work.
- 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_69ad8580c72481909672d37acf647893 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada546a6648190bc4bc3e599e6aa95 |
completed | March 8, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69ad9df62e548190b053e1478deed467 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada0f7c21c819087e9992f5fe30a37 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:04 p.m.