Triple
T10494329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Léon: The Professional |
E247495
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Ellen Greene |
E443591
|
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: Ellen Greene | Statement: [Léon: The Professional, castMember, Ellen Greene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ellen Greene Context triple: [Léon: The Professional, castMember, Ellen Greene]
-
A.
Ellen Greene
chosen
Ellen Greene is an American actress and singer best known for her distinctive voice and her role as Audrey in the musical and film "Little Shop of Horrors."
-
B.
Ellen Andrews
Ellen Andrews is the mother who magically swaps bodies with her teenage daughter in the 1976 fantasy-comedy film "Freaky Friday."
-
C.
Ellen Drew
Ellen Drew was an American film actress prominent in the late 1930s and 1940s, known for her roles in Hollywood dramas, comedies, and film noirs.
-
D.
Ellen Lacey
Ellen Lacey is a fictional character from the 1954 film noir "Crime Wave," involved in the story’s tense criminal underworld and police investigation.
-
E.
Ellen Louise
Ellen Louise was the wife of American film actor Robert Armstrong, best known for his role in the classic movie "King Kong."
- 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_69d381c309b88190af78aa681cf6a4c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5097fe2bc81909d66ce43f3533284 |
completed | April 7, 2026, 1:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d96b31de8c8190996df69ae02278f8 |
completed | April 10, 2026, 9:27 p.m. |
Created at: April 6, 2026, 12:24 p.m.