Triple
T17928884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howard Stern |
E448273
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Debra Jennifer Stern |
—
|
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: Debra Jennifer Stern | Statement: [Howard Stern, child, Debra Jennifer Stern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Debra Jennifer Stern Context triple: [Howard Stern, child, Debra Jennifer Stern]
-
A.
Debra Jennifer Stern
chosen
Debra Jennifer Stern is one of the daughters of American radio and television personality Howard Stern.
-
B.
Erica Steinberg
Erica Steinberg is a film producer known for her work on projects such as the 2015 movie "Victor Frankenstein."
-
C.
Kerri Eisenberg
Kerri Eisenberg is an American actress and voice actress known for her work in film and television, and as the older sister of actress Hallie Kate Eisenberg.
-
D.
Stacey Mindich
Stacey Mindich is a Tony Award–winning American theater producer best known for shepherding the hit Broadway musical "Dear Evan Hansen."
-
E.
Deborah Colker
Deborah Colker is a renowned Brazilian choreographer and director known for her innovative, physically daring contemporary dance works and collaborations with major international productions.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a5511a408190973cf5fa1f286a26 |
completed | April 19, 2026, 9:50 a.m. |
Created at: April 10, 2026, 10:20 a.m.