Triple
T25212218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Gershwin Connection |
E631718
|
entity |
| Predicate | includesLyricsBy |
P18290
|
FINISHED |
| Object | Ira Gershwin |
—
|
NE NERFINISHED |
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: Ira Gershwin | Statement: [The Gershwin Connection, includesLyricsBy, Ira Gershwin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesLyricsBy Context triple: [The Gershwin Connection, includesLyricsBy, Ira Gershwin]
-
A.
hasLyricsIn
Indicates that the lyrics of a work are written or available in a specified language.
-
B.
hasLyric
chosen
Indicates that one entity (typically a musical work or track) contains or is associated with the lyrics provided by another entity.
-
C.
hasAdditionalLyricsBy
Indicates that an entity (such as a musical work or track) includes extra or modified lyrics contributed by a specified person or group beyond the original lyricist.
-
D.
includesMusicAndLyrics
Indicates that something contains both the musical composition and the accompanying song lyrics as integral parts.
-
E.
hasLyricsFeature
Indicates that something possesses a particular characteristic or attribute related to its lyrics.
- 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_69e75a8d1aa48190a4320acd3654762c |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f6c1265c208190aacd2b551f8f0f82 |
completed | May 3, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2415fc81908c23c311aebce66f |
completed | May 3, 2026, 3:12 a.m. |
Created at: April 21, 2026, 12:58 p.m.