Triple
T10945047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fay Wray |
E258572
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sanford Rothenberg |
E70202
|
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: Sanford Rothenberg | Statement: [Fay Wray, spouse, Sanford Rothenberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sanford Rothenberg Context triple: [Fay Wray, spouse, Sanford Rothenberg]
-
A.
Sanford Rothenberg
chosen
Sanford Rothenberg was the second husband of actress Fay Wray, known primarily for his marriage to the iconic King Kong star.
-
B.
Ralph Alswang
Ralph Alswang was an American theater architect and designer known for his influential work on major Broadway venues and stage productions.
-
C.
Larry A. Lebofsky
Larry A. Lebofsky is an American astronomer known for his work in planetary science and the study of ring systems around planets.
-
D.
Jay O. Rothman
Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
-
E.
Richard A. Roth
Richard A. Roth is an American film producer best known for his work on the 1986 crime thriller "Manhunter."
- 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770e9a89081908979efd1d9e6af66 |
completed | April 9, 2026, 9:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f74602a7ec8190980e5e6a80aa1235 |
completed | May 3, 2026, 12:56 p.m. |
Created at: April 8, 2026, 9:23 p.m.