Triple
T118033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Marseillaise |
E2384
|
entity |
| Predicate | hasLyricsTheme |
P7609
|
FINISHED |
| Object | defense of the homeland |
—
|
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: defense of the homeland | Statement: [La Marseillaise, hasLyricsTheme, defense of the homeland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLyricsTheme Context triple: [La Marseillaise, hasLyricsTheme, defense of the homeland]
-
A.
lyricsBy
Indicates that the lyrics of a song or musical work were written or authored by a specified person or entity.
-
B.
hasMelody
Indicates that one entity possesses, contains, or is characterized by a particular melody.
-
C.
hasChorus
Indicates that something (typically a song or musical piece) includes a chorus section as part of its structure.
-
D.
lyricist
Indicates that one entity is the writer of the words (lyrics) for a musical work associated with another entity.
-
E.
commonlySungStanzas
Indicates that certain stanzas of a song or poem are those most frequently sung or performed in practice.
- 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25646d5088190a057989c32da3a90 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a258de46888190835db2b21a093eaa |
completed | Feb. 28, 2026, 2:54 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.