Triple
T31049677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | These Are My Songs |
E791223
|
entity |
| Predicate | secondarySingle |
P195937
|
FINISHED |
| Object | Don't Sleep in the Subway |
—
|
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: Don't Sleep in the Subway | Statement: [These Are My Songs, secondarySingle, Don't Sleep in the Subway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondarySingle Context triple: [These Are My Songs, secondarySingle, Don't Sleep in the Subway]
-
A.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
-
B.
secondarySee
Indicates that one entity is referenced as an additional or alternative point of consultation or viewing in relation to another entity.
-
C.
primarySingle
Indicates that an entity has exactly one main or primary association of the specified type, with no additional concurrent primary associations.
-
D.
secondaryTarget
Indicates that an entity serves as an additional or subordinate target in relation to a primary target within a given context or action.
-
E.
secondaryLine
Indicates that something serves as a secondary or auxiliary line in relation to a primary or main line.
- 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_69f224cb08908190ba71ad9aa87518ed |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fdf5d05cc481909ec9e1b1f0784279 |
completed | May 8, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69fdf0cdd6948190838864ab3120dfa6 |
completed | May 8, 2026, 2:18 p.m. |
| PDg | Predicate description generation | batch_69fdf5cfa1ec8190b80d887fa1bfb4cf |
completed | May 8, 2026, 2:40 p.m. |
Created at: April 29, 2026, 9 p.m.