Triple
T19397703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Comedian |
E485235
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Jackie Burke |
—
|
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: Jackie Burke | Statement: [The Comedian, mainCharacter, Jackie Burke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jackie Burke Context triple: [The Comedian, mainCharacter, Jackie Burke]
-
A.
Jackie Burke
chosen
Jackie Burke is the resourceful middle-aged flight attendant and central protagonist of Elmore Leonard’s crime novel "Rum Punch," later adapted into the film "Jackie Brown."
-
B.
Jacqueline Daly
Jacqueline Daly is a daughter of the legendary American country music singer Tammy Wynette.
-
C.
Linda Litzke
Linda Litzke is a vain, fitness-obsessed gym employee in the dark comedy film "Burn After Reading," whose misguided schemes to fund cosmetic surgery drive much of the movie’s chaotic plot.
-
D.
Lisa Melendy
Lisa Melendy is the athletic director overseeing the varsity sports programs at Williams College.
-
E.
Betsy Brandt
Betsy Brandt is an American actress best known for her role as Marie Schrader on the television series "Breaking Bad."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62574edd08190b5456108d5e3907e |
completed | April 20, 2026, 1:09 p.m. |
Created at: April 10, 2026, 1:36 p.m.