Triple
T20324579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walther Rathenau |
E492298
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | AEG |
—
|
NE NERFINISHED |
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: AEG | Statement: [Walther Rathenau, employer, AEG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AEG Context triple: [Walther Rathenau, employer, AEG]
-
A.
AEG
chosen
AEG is a historic German electrical engineering and electronics company known for its pioneering role in power systems, appliances, and industrial technology.
-
B.
AEG Europe
AEG Europe is a leading live entertainment and sports company that owns and operates major venues and events across Europe.
-
C.
AEG power tools
AEG power tools is a brand of professional-grade electric power tools and equipment originally associated with the German electrical company AEG.
-
D.
Mann-Grundig
Mann-Grundig was a professional cycling team active in the 1960s and 1970s, known for competing in major European road races.
-
E.
Gorenje
Gorenje is a Slovenian home appliance manufacturer known for producing a wide range of kitchen and household appliances for the European and global markets.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4a0134081909113563e1c3ba68a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6778e59508190bfd7a3ce44d56a93 |
completed | April 20, 2026, 6:59 p.m. |
Created at: April 16, 2026, 11:21 a.m.