Triple
T11607490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elisabeth Eybers |
E275299
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Albert Wessels
Albert Wessels was a South African businessman best known for founding Toyota South Africa and helping establish the brand’s presence in the country.
|
E944079
|
NE FINISHED |
How this triple was built (4 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: Albert Wessels | Statement: [Elisabeth Eybers, spouse, Albert Wessels]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Albert Wessels Context triple: [Elisabeth Eybers, spouse, Albert Wessels]
-
A.
Cees Wessels
Cees Wessels is a Dutch music executive best known as the founder of the influential heavy metal and hard rock label Roadrunner Records.
-
B.
Willem Louw
Willem Louw is a person notable enough to be specifically cited as a bearer of the surname Louw, though detailed public information about his life or achievements is limited.
-
C.
Ben Louw
Ben Louw is an individual notable enough to be specifically cited as a prominent bearer of the surname Louw.
-
D.
Hendrik Louw
Hendrik Louw is a person notable enough to be recognized as a significant bearer of the surname Louw.
-
E.
Adriaan Louw
Adriaan Louw is a South African-born physical therapist and pain scientist known for his work on pain neuroscience education and chronic pain management.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Albert Wessels Triple: [Elisabeth Eybers, spouse, Albert Wessels]
Generated description
Albert Wessels was a South African businessman best known for founding Toyota South Africa and helping establish the brand’s presence in the country.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Albert Wessels Target entity description: Albert Wessels was a South African businessman best known for founding Toyota South Africa and helping establish the brand’s presence in the country.
-
A.
Cees Wessels
Cees Wessels is a Dutch music executive best known as the founder of the influential heavy metal and hard rock label Roadrunner Records.
-
B.
Willem Louw
Willem Louw is a person notable enough to be specifically cited as a bearer of the surname Louw, though detailed public information about his life or achievements is limited.
-
C.
Ben Louw
Ben Louw is an individual notable enough to be specifically cited as a prominent bearer of the surname Louw.
-
D.
Hendrik Louw
Hendrik Louw is a person notable enough to be recognized as a significant bearer of the surname Louw.
-
E.
Adriaan Louw
Adriaan Louw is a South African-born physical therapist and pain scientist known for his work on pain neuroscience education and chronic pain management.
- F. None of above. chosen
Provenance (5 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_69d6aaf84b548190ac072e4fb89ae18f |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d89551649c81908096ff392677442d |
completed | April 10, 2026, 6:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f018eeb0f48190aea4f55d787f807a |
completed | April 28, 2026, 2:18 a.m. |
| NEDg | Description generation | batch_69f01d7ab930819095eaae226ab55b80 |
completed | April 28, 2026, 2:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f043ddbfe481908e0c439dbd3e944f |
completed | April 28, 2026, 5:21 a.m. |
Created at: April 8, 2026, 9:38 p.m.