Triple
T14001659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rhea Perlman |
E336839
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Perlman |
E34027
|
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: Perlman | Statement: [Rhea Perlman, familyName, Perlman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perlman Context triple: [Rhea Perlman, familyName, Perlman]
-
A.
Panufnik
Panufnik is a Polish surname most prominently associated with composer Andrzej Panufnik and his daughter, British composer Roxanna Panufnik.
-
B.
Erik Friedlander
Erik Friedlander is an American cellist and composer known for his innovative work in avant-garde jazz, contemporary classical music, and genre-blending collaborations.
-
C.
Itzhak Perlman
chosen
Itzhak Perlman is an acclaimed Israeli-American violinist renowned for his virtuosity, rich tone, and interpretations of the classical repertoire.
-
D.
Chaja Rubinstein
Chaja Rubinstein, better known as Helena Rubinstein, was a pioneering Polish-American businesswoman who founded one of the world’s first global cosmetics empires.
-
E.
Michael Stern
Michael Stern is an American philanthropist and real estate developer best known for founding New York City's Intrepid Sea, Air & Space Museum.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ed06a50819093ddc64f55050689 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbaca180988190bbfc93bd708688d6 |
completed | May 6, 2026, 9:03 p.m. |
Created at: April 9, 2026, 10:19 p.m.