Triple
T11343881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Draper |
E268668
|
entity |
| Predicate | hasAffairWith |
P23617
|
FINISHED |
| Object | Rachel Menken |
E380303
|
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: Rachel Menken | Statement: [Don Draper, hasAffairWith, Rachel Menken]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rachel Menken Context triple: [Don Draper, hasAffairWith, Rachel Menken]
-
A.
Rachel Menken
chosen
Rachel Menken is a sophisticated, ambitious Jewish department store heiress and businesswoman in the television series "Mad Men," who becomes both a client and romantic interest of Don Draper.
-
B.
Rachel Leibowitz
Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
-
C.
Rachel Buchman
Rachel Buchman is the titular bride and central figure in the 2008 drama film "Rachel Getting Married," around whose wedding and family tensions the story revolves.
-
D.
Rachel Taub
Rachel Taub is a fictional character from the medical drama series "House," known as the wife of Dr. Chris Taub.
-
E.
Cynthia Malkin
Cynthia Malkin is an American heiress and philanthropist best known as the longtime wife of U.S. Senator Richard Blumenthal.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea1e360c8190a02d1e2d1d6f4b5d |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ee864bf89081909fa336393e59f073 |
completed | April 26, 2026, 9:40 p.m. |
Created at: April 8, 2026, 9:33 p.m.