Triple
T12685069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilde Benjamin |
E303045
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Ernst Meyer |
E285359
|
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: Ernst Meyer | Statement: [Hilde Benjamin, sibling, Ernst Meyer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ernst Meyer Context triple: [Hilde Benjamin, sibling, Ernst Meyer]
-
A.
Ernst Meyer
chosen
Ernst Meyer was a German socialist politician and revolutionary active in the early 20th century, associated with the radical left-wing movements that emerged around World War I.
-
B.
Joseph Weydemeyer
Joseph Weydemeyer was a German-American Marxist, military officer, and journalist who helped introduce and disseminate Karl Marx’s ideas in the United States.
-
C.
Franz Winkler
Franz Winkler is an Austrian mathematician and computer scientist known for his contributions to symbolic computation and computer algebra.
-
D.
George Engelmann
George Engelmann was a 19th-century German-American botanist and physician known for his pioneering taxonomic work on North American desert and mountain plants, including cacti and yuccas.
-
E.
Karl Butz
Karl Butz is a violinist and educator known for his contributions to string pedagogy and performance.
- 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_69d7bdee64a08190801c6d470aefd723 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961d7cd4c81909521839ef5859799 |
completed | April 10, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671a8f068819086e2191439607f76 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:21 p.m.