Triple
T16931624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Windsor |
E410722
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Marie Windsor |
E410722
|
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: Marie Windsor | Statement: [Marie Windsor, name, Marie Windsor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marie Windsor Context triple: [Marie Windsor, name, Marie Windsor]
-
A.
Marie Windsor
chosen
Marie Windsor was an American character actress best known for her tough, sultry roles in film noir and B-movies during the 1940s and 1950s.
-
B.
Vivien Merchant
Vivien Merchant was an English stage and film actress known for her intense performances in British drama during the 1960s and 1970s.
-
C.
Flora Robson
Flora Robson was a distinguished British actress known for her powerful character roles in both stage and film, often portraying strong, authoritative women.
-
D.
Polly Benedict
Polly Benedict is a recurring love interest of the title character in the classic "Andy Hardy" film series.
-
E.
Margaret Ashcroft
Margaret Ashcroft was a British actress known for her work in mid-20th-century film and television dramas.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cf25a6dc8190a2b9d9c4d2adc5fd |
completed | April 18, 2026, 6:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc024d7c8190b8055833ed8908d5 |
completed | May 10, 2026, 7:26 p.m. |
Created at: April 10, 2026, 5:30 a.m.