Triple
T8863059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martha Bernays |
E210939
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bernays |
E602272
|
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: Bernays | Statement: [Martha Bernays, familyName, Bernays]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bernays Context triple: [Martha Bernays, familyName, Bernays]
-
A.
Bernays
chosen
Bernays is a surname most notably associated with mathematician Paul Bernays and public relations pioneer Edward Bernays.
-
B.
Oppenheim
Oppenheim is a German-origin surname borne by various notable individuals across fields such as entertainment, finance, and academia.
-
C.
Löwenthal
Löwenthal is the maiden surname of Elsa Einstein, who was both the second wife and cousin of physicist Albert Einstein.
-
D.
Heilbron
Heilbron is a town in South Africa’s Free State province that historically served as a parliamentary constituency, including for figures such as Hendrik Verwoerd.
-
E.
Jeanneret
Jeanneret is a Swiss surname most notably associated with architect Pierre Jeanneret, a key collaborator of Le Corbusier in modernist architecture.
- 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_69ca838bbddc8190ab546d737e5d350f |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc610416b48190a26f0c457089ffca |
completed | April 1, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0caccd88190b6464f53d0239e47 |
completed | April 3, 2026, 11:13 a.m. |
Created at: March 30, 2026, 6:50 p.m.