Triple
T2236276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katia Mann |
E49287
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Elisabeth Mann Borgese |
E42636
|
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: Elisabeth Mann Borgese | Statement: [Katia Mann, child, Elisabeth Mann Borgese]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elisabeth Mann Borgese Context triple: [Katia Mann, child, Elisabeth Mann Borgese]
-
A.
Elisabeth Mann Borgese
chosen
Elisabeth Mann Borgese was a German-born writer and pioneering advocate for international ocean governance and the law of the sea.
-
B.
Helen Gardner
Helen Gardner is a noted literary scholar and critic, best known for her influential work on English poetry and Renaissance literature.
-
C.
Marianne Ehrlich
Marianne Ehrlich was the daughter of Nobel Prize–winning German physician and immunologist Paul Ehrlich.
-
D.
Sara Danius
Sara Danius was a Swedish scholar of literature and aesthetics who became the first female permanent secretary of the Swedish Academy, the body that awards the Nobel Prize in Literature.
-
E.
Helen Wolff
Helen Wolff was a distinguished German-American editor and publisher renowned for bringing important European literature to English-speaking audiences, notably through her work at Pantheon Books.
- 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc093ba0c819091df09a0e018fce1 |
completed | March 7, 2026, 6:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae7f007e988190bb032a39cfea7730 |
completed | March 9, 2026, 8:04 a.m. |
Created at: March 4, 2026, 7:47 p.m.