Triple
T22974269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mission Hill |
E571269
|
entity |
| Predicate | protagonist |
P268
|
FINISHED |
| Object | Andy French |
—
|
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: Andy French | Statement: [Mission Hill, protagonist, Andy French]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andy French Context triple: [Mission Hill, protagonist, Andy French]
-
A.
Andy French
chosen
Andy French is the slacker, aspiring cartoonist protagonist of the animated television series "Mission Hill," known for his laid-back attitude and struggles with adulthood.
-
B.
Kevin French
Kevin French is the neurotic, academically driven teenage protagonist of the animated television series "Mission Hill."
-
C.
Louie French
Louie French is a British Conservative Party politician and Member of Parliament.
-
D.
Michael Paré
Michael Paré is an American actor best known for his roles in 1980s and 1990s films such as "Eddie and the Cruisers" and "Streets of Fire."
-
E.
Steven French
Steven French is a philosopher of science known for his work on the metaphysics of science, particularly structural realism and the philosophy of physics.
- 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_69e245b2c6548190a0e4c7f2f7df2d48 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182350b448190a34e5fa0167fd964 |
completed | April 29, 2026, 3:59 a.m. |
Created at: April 17, 2026, 3:48 p.m.