Triple
T2263165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frederick Austerlitz |
E50083
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Robyn Smith |
E164687
|
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: Robyn Smith | Statement: [Frederick Austerlitz, spouse, Robyn Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robyn Smith Context triple: [Frederick Austerlitz, spouse, Robyn Smith]
-
A.
Robyn Smith
chosen
Robyn Smith is an American jockey and actress best known for being the much younger third wife of legendary dancer and actor Fred Astaire.
-
B.
Nina Smith
Nina Smith is known as one of the children of American rapper and actor LL Cool J.
-
C.
Malissa Smith
Malissa Smith is a member of the Smith family and a sibling of Joseph Smith, the founder of the Latter Day Saint movement.
-
D.
Simone Smith
Simone Smith is an American jewelry designer and entrepreneur best known for her long-term marriage to rapper and actor LL Cool J and her work in fashion and philanthropy.
-
E.
Rose Smith
Rose Smith is a central daughter in the Smith family and a romantic lead in the classic 1944 MGM musical film "Meet Me in St. Louis."
- 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_69a88b01e0048190ba96431b5f990ba9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc18d7fc08190851765683d1b8092 |
completed | March 7, 2026, 6:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b030fc819c8190a1bd9bba49760fec |
completed | March 10, 2026, 2:55 p.m. |
Created at: March 4, 2026, 7:48 p.m.