Triple
T21618494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madame de Garderobe |
E533509
|
entity |
| Predicate | supportsCharacter |
P16523
|
FINISHED |
| Object | Belle |
—
|
NE NERFINISHED |
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: Belle | Statement: [Madame de Garderobe, supportsCharacter, Belle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Belle Context triple: [Madame de Garderobe, supportsCharacter, Belle]
-
A.
Belle
Belle is a supporting character in the 2018 heist thriller film "Widows," involved in the criminal plot led by a group of women in Chicago.
-
B.
Belle
Belle is a British television drama film featuring Thomas Geoffrey Wilkinson in a prominent role.
-
C.
Belle
chosen
Belle is a 2013 British period drama film inspired by the true story of Dido Elizabeth Belle, a mixed-race woman raised in an aristocratic English family, exploring themes of race, class, and social justice.
-
D.
Belle
Belle is the given name of Beverly Sills, the celebrated American operatic soprano and arts administrator.
-
E.
Belle
Belle is a fictional saloon entertainer and love interest in the British Western parody film "Carry On Cowboy."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46411108190bba0d4176dffc9f3 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef3bac4a5c8190919c625c14a54c16 |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 16, 2026, 6:34 p.m.