Triple
T4562481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marianne von Weizsäcker |
E121825
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Karl Carstens |
E196551
|
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: Karl Carstens | Statement: [Marianne von Weizsäcker, relative, Karl Carstens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karl Carstens Context triple: [Marianne von Weizsäcker, relative, Karl Carstens]
-
A.
Karl Carstens
chosen
Karl Carstens was a German politician and statesman who served as President of the Federal Republic of Germany from 1979 to 1984.
-
B.
Puncak Jaya
Puncak Jaya is the highest mountain in Oceania, located in the Sudirman Range of Papua, Indonesia, and is one of the Seven Summits.
-
C.
Thomas Everest
Thomas Everest was the father of Mary Everest, who became a notable mathematician and educator.
-
D.
Mount Tambuyukon
Mount Tambuyukon is a high, biodiverse mountain in Sabah, Malaysian Borneo, known for its rich montane ecosystems and rare endemic species.
-
E.
Mount Dikti
Mount Dikti is a prominent mountain massif in eastern Crete, Greece, known for its rugged peaks, rich biodiversity, and mythological association as the birthplace of the god Zeus.
- 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_69bd463f156881908a99aca69c5721ac |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd582f21648190b49284eb61b618c9 |
completed | March 20, 2026, 2:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdc5a2a97081909c9c064924fcaa22 |
completed | March 20, 2026, 10:09 p.m. |
Created at: March 20, 2026, 1:09 p.m.