Triple
T17145222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Cera |
E416073
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Cera |
E416073
|
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: Cera | Statement: [Michael Cera, familyName, Cera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cera Context triple: [Michael Cera, familyName, Cera]
-
A.
Cera
chosen
Cera is the surname of Canadian actor Michael Cera, known for his roles in films like "Superbad" and the series "Arrested Development."
-
B.
Kera
Kera is a regional dialect of the Mundari language spoken by sections of the Munda ethnic community in eastern India.
-
C.
Caron
Caron is a French surname most famously associated with actress and dancer Leslie Caron, known for her roles in classic Hollywood musicals.
-
D.
Marzelline
Marzelline is a character in Beethoven's opera "Fidelio," portrayed as the jailer Rocco’s daughter who becomes romantically entangled with the disguised heroine.
-
E.
Tamra
Tamra is an Arab town in northern Israel that became part of the state during the 1948 Arab–Israeli War and has since developed into a significant local center for the region’s Arab community.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2da515481909d19e421382eb755 |
completed | April 18, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014158ed8c8190adb3c03c8a114a59 |
completed | May 11, 2026, 2:39 a.m. |
Created at: April 10, 2026, 5:36 a.m.