Triple
T12448931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herman J. Mankiewicz |
E297477
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sara Aaronson |
E297477
|
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: Sara Aaronson | Statement: [Herman J. Mankiewicz, spouse, Sara Aaronson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sara Aaronson Context triple: [Herman J. Mankiewicz, spouse, Sara Aaronson]
-
A.
Sara Aaronson
chosen
Sara Aaronson was the wife of American screenwriter Herman J. Mankiewicz, known for her connection to the prominent Hollywood writer behind "Citizen Kane."
-
B.
Sara Adler
Sara Adler was a prominent Yiddish theater actress and influential figure in early 20th-century American Jewish stage culture.
-
C.
Sari Gilman
Sari Gilman is a film editor best known for her work on the Academy Award–winning documentary "Taxi to the Dark Side."
-
D.
Rachel Resnick
Rachel Resnick is an American author and memoirist known for her candid, often humorous explorations of personal relationships and emotional vulnerability.
-
E.
Arianna W. Rosenbluth
Arianna W. Rosenbluth was an American physicist and pioneering computer scientist best known for her foundational role in developing the Metropolis algorithm, a cornerstone of modern Markov chain Monte Carlo methods.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d9e592c81908cf7f3ca170d942c |
completed | April 10, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ea710d481908371209cb92502a6 |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 8, 2026, 9:56 p.m.