Triple
T7524829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonia Rykiel |
E177864
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sam Rykiel |
E177864
|
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: Sam Rykiel | Statement: [Sonia Rykiel, spouse, Sam Rykiel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sam Rykiel Context triple: [Sonia Rykiel, spouse, Sam Rykiel]
-
A.
Sonia Rykiel
chosen
Sonia Rykiel was a renowned French fashion designer celebrated for her chic knitwear, left-bank Parisian style, and influential eponymous label.
-
B.
Jonathan Sachs
Jonathan Sachs is an American software developer best known as a co-founder of Lotus Development Corporation and co-creator of the Lotus 1-2-3 spreadsheet program.
-
C.
Diane von Fürstenberg
Diane von Fürstenberg is a Belgian-born fashion designer best known for creating the iconic wrap dress and founding her eponymous global luxury brand.
-
D.
Thomas Jacob Hilfiger
Thomas Jacob Hilfiger is an American fashion designer best known as the founder of the global lifestyle brand Tommy Hilfiger.
-
E.
Halston Sage
Halston Sage is an American actress best known for her role as Lieutenant Alara Kitan on the science fiction television series "The Orville."
- 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_69c69f29bf3081909a146aec7755f185 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f7c61b508190b582f54ecbb387e3 |
completed | March 27, 2026, 9:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84631e6bc819099b3a7819c3ae9a7 |
completed | March 28, 2026, 9:20 p.m. |
Created at: March 27, 2026, 3:46 p.m.