Triple
T7275007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theodor Mommsen |
E163003
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Marie Reimer |
E163003
|
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: Marie Reimer | Statement: [Theodor Mommsen, spouse, Marie Reimer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marie Reimer Context triple: [Theodor Mommsen, spouse, Marie Reimer]
-
A.
Marie Reimer
chosen
Marie Reimer was the wife of renowned German classical scholar and historian Theodor Mommsen.
-
B.
Louise Mueller
Louise Mueller is a notable individual who shares the surname Mueller and has achieved sufficient recognition to be distinguished among its bearers.
-
C.
Marie Meyer
Marie Meyer was the wife of the prominent German historian Eduard Meyer.
-
D.
Winifred Reed Landis
Winifred Reed Landis was the wife of longtime Major League Baseball commissioner and federal judge Kenesaw Mountain Landis.
-
E.
Marie Gundert
Marie Gundert was the mother of German-Swiss writer and Nobel laureate Hermann Hesse, belonging to a family deeply involved in Christian missionary and educational work.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb0fd8788190aa21d4b2ad773926 |
completed | March 27, 2026, 8:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c81eb53060819081312e8b2805e9db |
completed | March 28, 2026, 6:32 p.m. |
Created at: March 27, 2026, 2:58 p.m.