Triple
T9987655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Velvet |
E196809
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Sandy Williams |
E219956
|
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: Sandy Williams | Statement: [Blue Velvet, mainCharacter, Sandy Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandy Williams Context triple: [Blue Velvet, mainCharacter, Sandy Williams]
-
A.
Sandy Williams
chosen
Sandy Williams is the naive yet courageous small-town college student Laura Dern portrays in David Lynch’s neo-noir film "Blue Velvet."
-
B.
Marlene Little
Marlene Little is known as the wife of Australian Aboriginal musician and entertainer Jimmy Little.
-
C.
Sheila Williams
Sheila Williams is an acclaimed science fiction editor best known for her long tenure as editor of Asimov’s Science Fiction magazine.
-
D.
Letitia Lewis
Letitia Lewis is a bold, resourceful young Black woman navigating supernatural horrors and racist violence in mid-20th-century America in the TV series "Lovecraft Country."
-
E.
Marlorie Jones
Marlorie Jones is the mother of Jamaican-American singer, model, and actress Grace Jones.
- 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_69ca82f1678c819093d06320a05f16a4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdc79c8b80819091dc16ac8fd0c720 |
completed | April 2, 2026, 1:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d25810584c81908382cf6edd700530 |
completed | April 5, 2026, 12:39 p.m. |
Created at: March 30, 2026, 8:50 p.m.