Triple
T15683174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruth Perelman |
E377629
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Raymond G. Perelman |
E69157
|
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: Raymond G. Perelman | Statement: [Ruth Perelman, spouse, Raymond G. Perelman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raymond G. Perelman Context triple: [Ruth Perelman, spouse, Raymond G. Perelman]
-
A.
Raymond G. Perelman
chosen
Raymond G. Perelman was an American businessman and philanthropist known for his major charitable contributions to education, medicine, and the arts, particularly at the University of Pennsylvania.
-
B.
Kenneth Posner
Kenneth Posner is a prominent American theatrical lighting designer known for his work on numerous Broadway productions.
-
C.
Roy R. Neuberger
Roy R. Neuberger was an American financier, philanthropist, and prominent modern art collector who played a key role in supporting and promoting 20th-century artists.
-
D.
Daniel H. Lowenstein
Daniel H. Lowenstein is a prominent American legal scholar known for his pioneering work in election law and political reform.
-
E.
Michael D. Ratner
Michael D. Ratner is an American director and producer known for his work on high-profile music videos, documentaries, and branded content for major artists and entertainment brands.
- 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f31b5b881908e46ecd9fc6048ab |
completed | April 16, 2026, 2:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ee4c8688190ae2fefb56171161a |
completed | May 9, 2026, 5:29 p.m. |
Created at: April 10, 2026, 4:16 a.m.