Triple
T1070525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Jane Gumm |
E23315
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Pat Gumm |
E126754
|
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: Pat Gumm | Statement: [Mary Jane Gumm, sibling, Pat Gumm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pat Gumm Context triple: [Mary Jane Gumm, sibling, Pat Gumm]
-
A.
Frank Gumm
Frank Gumm was an American vaudeville performer and theater owner best known as the father of legendary entertainer Judy Garland.
-
B.
Jimmie Gumm
chosen
Jimmie Gumm is a member of the Gumm family, known primarily as a sibling of Mary Jane Gumm, part of the family connected to entertainer Judy Garland.
-
C.
Willie
Willie is the first name of Willie Nelson, the iconic American country music singer-songwriter and cultural figure.
-
D.
Ado Annie Carnes
Ado Annie Carnes is a flirtatious, comedic supporting character in the musical "Oklahoma!" known for her indecisiveness about love and her signature song "I Cain't Say No."
-
E.
Barney Fife
Barney Fife is the bumbling yet well-meaning deputy sheriff of Mayberry, best known as Andy Taylor’s overzealous sidekick on the classic American sitcom "The Andy Griffith Show."
- 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_69a493ee1f908190992b5f0d1b04459b |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b92848148190ba8795cb8d0a1d0a |
completed | March 1, 2026, 10:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac538856b481908d6a25ee05fb4885 |
completed | March 7, 2026, 4:34 p.m. |
Created at: March 1, 2026, 7:42 p.m.