Triple
T23477629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I'm Not Rappaport |
E570308
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Herb Gardner |
—
|
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: Herb Gardner | Statement: [I'm Not Rappaport, writer, Herb Gardner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herb Gardner Context triple: [I'm Not Rappaport, writer, Herb Gardner]
-
A.
Herb Gardner
chosen
Herb Gardner was an American playwright, screenwriter, and cartoonist best known for works like "A Thousand Clowns" and "I'm Not Rappaport."
-
B.
George L. Dahl
George L. Dahl was a prominent 20th-century American architect known for shaping much of Dallas’s skyline and major civic landmarks.
-
C.
Vernon Demerest
Vernon Demerest is a confident, hotshot airline pilot whose personal and professional crises drive much of the drama in the 1970 disaster film "Airport."
-
D.
Charles Guggenheim
Charles Guggenheim was an American documentary filmmaker renowned for his politically engaged and historically focused films, earning multiple Academy Awards over his career.
-
E.
Irving Gordon
Irving Gordon was an American songwriter best known for penning enduring standards such as "Unforgettable" and other popular mid-20th-century ballads.
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74dbea8819085ca84391039e7f7 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:02 p.m.