Triple
T23411782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carlos |
E560087
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Dan Franck |
—
|
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: Dan Franck | Statement: [Carlos, writer, Dan Franck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Franck Context triple: [Carlos, writer, Dan Franck]
-
A.
Dan Franck
chosen
Dan Franck is a French novelist and screenwriter known for his historical and political works, including collaborations on acclaimed television miniseries.
-
B.
Dan Frank
Dan Frank was an influential American book editor known for shaping contemporary literary fiction and nonfiction during his long tenure at major publishing houses.
-
C.
Dan Janvey
Dan Janvey is an American film producer known for his work on acclaimed independent films, including the Academy Award–winning "Nomadland."
-
D.
Dan Eckman
Dan Eckman is an American director, writer, and producer best known for his work with the comedy group Derrick Comedy and for directing the feature film "Mystery Team."
-
E.
Leon Fromkess
Leon Fromkess was an American film producer active during Hollywood’s studio era, known for overseeing a variety of mid-20th-century motion pictures.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a51183bc8190bd4860607b26b4b2 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:38 p.m.