Triple
T5361042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ben Mendelsohn |
E103020
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Mendelsohn |
E277401
|
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: Mendelsohn | Statement: [Ben Mendelsohn, familyName, Mendelsohn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mendelsohn Context triple: [Ben Mendelsohn, familyName, Mendelsohn]
-
A.
Mendelsohn
chosen
Mendelsohn is the surname of Erich Mendelsohn, a pioneering German architect known for his influential Expressionist and modernist designs.
-
B.
Ussishkin
Ussishkin is a Jewish family name most prominently associated with Zionist leader Menachem Ussishkin.
-
C.
Meyer Suchowljansky
Meyer Suchowljansky, better known as Meyer Lansky, was a major organized crime figure in the United States who helped develop the National Crime Syndicate and became known as the "Mob's Accountant."
-
D.
Moritz
Moritz is a masculine given name of German origin, commonly used in German-speaking countries.
-
E.
Gershon
Gershon is the surname of American actress Gina Gershon, known for her roles in films like "Showgirls" and "Bound."
- 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_69bd43daa3e4819090b59d127db70e57 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd86588af081908c846fcde65724da |
completed | March 20, 2026, 5:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf21ec83b88190abc227d93b4c1c49 |
completed | March 21, 2026, 10:55 p.m. |
Created at: March 20, 2026, 2:02 p.m.