Triple
T7024879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sullivan's Travels |
E162917
|
entity |
| Predicate | leadActress |
P6108
|
FINISHED |
| Object | Veronica Lake |
E31920
|
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: Veronica Lake | Statement: [Sullivan's Travels, leadActress, Veronica Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Veronica Lake Context triple: [Sullivan's Travels, leadActress, Veronica Lake]
-
A.
Veronica Lake
chosen
Veronica Lake was a popular American film actress of the 1940s, famed for her roles in film noir and her iconic peek-a-boo hairstyle.
-
B.
Volga Hayworth
Volga Hayworth was the mother of Hollywood actress Rita Hayworth and part of the family background that shaped the star's early life.
-
C.
Barbara La Marr
Barbara La Marr was a popular American silent film actress and screenwriter of the early 1920s, often billed as "The Girl Who Is Too Beautiful."
-
D.
Jo Harlow
Jo Harlow is a technology executive best known for leading mobile device and smartphone businesses at companies such as Nokia and later Microsoft.
-
E.
Jean Harlow
Jean Harlow was a legendary American film actress and 1930s sex symbol known for her platinum blonde image and starring roles in early Hollywood comedies and 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_69c6885b26248190a857541e3d10e299 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e1fb8f0c8190b15dd7ce7ab6a8f2 |
completed | March 27, 2026, 8 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7bf7363b88190a082915ebac4f575 |
completed | March 28, 2026, 11:45 a.m. |
Created at: March 27, 2026, 2:35 p.m.