Triple
T26204948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | One More Car, One More Rider |
E655335
|
entity |
| Predicate | backingBandMember |
P155224
|
FINISHED |
| Object | Katie Kissoon |
—
|
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: Katie Kissoon | Statement: [One More Car, One More Rider, backingBandMember, Katie Kissoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: backingBandMember Context triple: [One More Car, One More Rider, backingBandMember, Katie Kissoon]
-
A.
houseBandMember
Indicates that a person is a member of a house band, typically performing regularly as part of that resident musical group.
-
B.
hasBackingBandMembers
chosen
Indicates that a musical act or performer is associated with specific individuals who serve as members of their backing band.
-
C.
contributingBandMember
Indicates that an individual is a member of a band who contributes to its music, performance, or creative output.
-
D.
originalBandMember
Indicates that a person was part of the band’s lineup at the time the band was first formed.
-
E.
hasBandMember
Indicates that a musical group includes a specific individual as one of its members.
- 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f62d89b89c8190afb372a8172111e7 |
completed | May 2, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 26, 2026, 8:50 p.m.