Triple
T13056347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tribute to Uncle Ray |
E327584
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Mary Ann |
E497458
|
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: Mary Ann | Statement: [Tribute to Uncle Ray, hasTrack, Mary Ann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Ann Context triple: [Tribute to Uncle Ray, hasTrack, Mary Ann]
-
A.
Mary Ann
Mary Ann is the namesake of the city of Marianna in Florida.
-
B.
Mary Ann
chosen
"Mary Ann" is a song by the American punk rock band Squirtgun, recognized as one of their more notable tracks.
-
C.
Mary Ann Day
Mary Ann Day was the second wife of American abolitionist John Brown and the mother of several of his children, who supported his family during his militant anti-slavery activities.
-
D.
Mary Ann Pearce
Mary Ann Pearce is known as the wife of American crime novelist Mickey Spillane.
-
E.
Eliza Ann Smith
Eliza Ann Smith was the first wife of American politician and future Chief Justice Salmon P. Chase, with whom she had several children before her early death.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d980bd305c8190bcf191b2d35ec8de |
completed | April 10, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbdead348190aa7aaa29c371d72a |
completed | May 3, 2026, 4:15 a.m. |
Created at: April 9, 2026, 8:58 p.m.