Triple
T17170731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margo Lion |
E416724
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Jelly’s Last Jam |
E140539
|
NE 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: Jelly’s Last Jam | Statement: [Margo Lion, notableWork, Jelly’s Last Jam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jelly’s Last Jam Context triple: [Margo Lion, notableWork, Jelly’s Last Jam]
-
A.
Jelly's Last Jam
chosen
Jelly's Last Jam is a Broadway musical that dramatizes the life and legacy of jazz pioneer Jelly Roll Morton through music, dance, and storytelling.
-
B.
Jelly Jelly
"Jelly Jelly" is a song featured on the album "Brothers and Sisters" by the Allman Brothers Band.
-
C.
Jam Up and Jelly Tight
"Jam Up and Jelly Tight" is a 1969 bubblegum pop hit single by American singer-songwriter Tommy Roe, known for its catchy melody and playful lyrics.
-
D.
Jelly, Jelly
"Jelly, Jelly" is a jazz and blues standard popularized by vocalist and bandleader Billy Eckstine in the 1940s.
-
E.
Shifty Jelly
Shifty Jelly is an Australian app development studio best known for creating the popular podcast app Pocket Casts.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3fc097950819095631ee5679e03af |
completed | April 18, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01483f85648190acaeb197013e1f1b |
completed | May 11, 2026, 3:08 a.m. |
Created at: April 10, 2026, 5:37 a.m.