Triple
T17128148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karl Lehmann |
E415651
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Lehmann |
E1158524
|
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: Lehmann | Statement: [Karl Lehmann, familyName, Lehmann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lehmann Context triple: [Karl Lehmann, familyName, Lehmann]
-
A.
Lehmann
chosen
Lehmann is a German-language surname borne by numerous notable individuals across fields such as science, politics, sports, and the arts.
-
B.
Lehmann and Neumann
Lehmann and Neumann were microbiologists who formally described and named the bacterial genus Mycobacterium.
-
C.
Thielmann
Thielmann is a German surname most notably associated with Johann von Thielmann, a distinguished general in the Napoleonic Wars.
-
D.
Wesselmann
Wesselmann is a surname most notably associated with Tom Wesselmann, a prominent American Pop Art painter known for his bold, stylized depictions of the nude and everyday consumer objects.
-
E.
Hufstedler
Hufstedler is the surname of Shirley Hufstedler, a prominent American judge and the first U.S. Secretary of Education.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f0285a408190ae5e4c4679c07fbf |
completed | April 18, 2026, 8:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01414a51d4819086c2346fe2d4fce4 |
completed | May 11, 2026, 2:39 a.m. |
Created at: April 10, 2026, 5:36 a.m.