Triple
T20644908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michelle Lavigne |
E507329
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Michelle |
—
|
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: Michelle | Statement: [Michelle Lavigne, givenName, Michelle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michelle Context triple: [Michelle Lavigne, givenName, Michelle]
-
A.
Michelle
Michelle is the resourceful and determined protagonist of the psychological thriller film "10 Cloverfield Lane."
-
B.
Michelle
chosen
Michelle is a common given name, typically the feminine form of Michael, used in many English- and French-speaking countries.
-
C.
Michelle
Michelle is the central teenage protagonist in the 2003 drama film "Elephant," which portrays the events leading up to a high school shooting.
-
D.
Michelle
Michelle is a character from Denis Johnson’s short story collection *Jesus’ Son*, depicted as one of the troubled, transient figures orbiting the drug-addicted narrator’s life.
-
E.
Michelle
Michelle is a Fossil Group watch and accessories brand known for its fashion-forward, feminine designs and luxury-inspired styling.
- 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_69e0b4be702c8190a3d2410a881d310a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af1dd79481909de985d03ab861c2 |
completed | April 20, 2026, 10:56 p.m. |
Created at: April 16, 2026, 11:43 a.m.