Triple
T23032713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jon Bernthal |
E573505
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bernthal |
—
|
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: Bernthal | Statement: [Jon Bernthal, familyName, Bernthal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bernthal Context triple: [Jon Bernthal, familyName, Bernthal]
-
A.
Bernthal
chosen
Bernthal is a surname most notably associated with American actor Jon Bernthal, known for his intense roles in film and television.
-
B.
Wulpen
Wulpen is a village and municipal section of the coastal town of Koksijde in West Flanders, Belgium.
-
C.
Feustel
Feustel is the surname of Andrew J. Feustel, an American geophysicist and NASA astronaut known for his space shuttle and International Space Station missions.
-
D.
Speer
Speer is a German surname most famously associated with Albert Speer, the Nazi architect and Minister of Armaments and War Production during World War II.
-
E.
Borchardt
Borchardt is a German surname most notably associated with Ludwig Borchardt, the archaeologist who discovered the bust of Nefertiti.
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18482e78c8190a89681eec2edb812 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.