Triple
T10070454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peggy Rajski |
E213609
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Peggy Rajski |
E213609
|
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: Peggy Rajski | Statement: [Peggy Rajski, name, Peggy Rajski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peggy Rajski Context triple: [Peggy Rajski, name, Peggy Rajski]
-
A.
Peggy Rajski
chosen
Peggy Rajski is an American film producer and director best known for producing the Oscar-winning short film "Trevor" and co-founding The Trevor Project, a leading LGBTQ youth crisis intervention organization.
-
B.
Vicki Sirotta
Vicki Sirotta is a film producer best known for her work on the horror-thriller movie "The Prophecy."
-
C.
Peggy Johnson
Peggy Johnson was the second wife of famed American automobile executive Lee Iacocca.
-
D.
Beverly Barish
Beverly Barish is a scheming antagonist in the comedy film "Tommy Boy," posing as Tommy's stepmother while secretly plotting to take over his family's auto parts company.
-
E.
Pamela Vaccaro
Pamela Vaccaro is known as the wife of influential American sports marketing executive Sonny Vaccaro.
- 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_69ca839add308190b57d53b4ec21f2d0 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcffa045c8190a08db0bb74cb006a |
completed | April 2, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dff74d59f88190bbd975521b16ae49 |
completed | April 15, 2026, 8:38 p.m. |
Created at: March 30, 2026, 8:58 p.m.