Triple
T3422796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Women (1933 film) |
E72151
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Joan Bennett |
E342141
|
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: Joan Bennett | Statement: [Little Women (1933 film), starring, Joan Bennett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joan Bennett Context triple: [Little Women (1933 film), starring, Joan Bennett]
-
A.
Joan Bennett
chosen
Joan Bennett was a prominent American film actress of the 1930s and 1940s, known for her transition from blonde ingenue roles to sultry film noir femme fatales under director Fritz Lang.
-
B.
Dina Merrill
Dina Merrill was an American actress, heiress, and philanthropist known for her elegant screen presence in mid-20th-century Hollywood films and television.
-
C.
Evelyn Keyes
Evelyn Keyes was an American film actress best known for her role as Suellen O'Hara in the classic 1939 film "Gone with the Wind."
-
D.
Nancy Richardson
Nancy Richardson is a film editor best known for her work on movies such as the biographical sports comedy-drama "Fighting with My Family."
-
E.
Phyllis Fraser
Phyllis Fraser was an American actress-turned-publishing executive and children's book editor who co-founded Beginner Books and played a key role in popularizing early readers like those by Dr. Seuss.
- 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_69ad85ad38e48190b7660c5118a35289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb95223e081908b2954769d2f46c8 |
completed | March 8, 2026, 6 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b672133044819089d54cca5ed6a063 |
completed | March 15, 2026, 8:47 a.m. |
Created at: March 8, 2026, 3:15 p.m.