Triple
T18637871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rolf de Heer |
E455601
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
de Heer
de Heer is a Dutch-origin surname borne by various notable individuals, including Australian film director Rolf de Heer.
|
E1335431
|
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: de Heer | Statement: [Rolf de Heer, familyName, de Heer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: de Heer Context triple: [Rolf de Heer, familyName, de Heer]
-
A.
De Wit
De Wit is a Dutch surname commonly borne by individuals of Dutch origin and often associated with historical figures from the Netherlands.
-
B.
De Haan
De Haan is a seaside resort town on the Belgian coast, known for its Belle Époque architecture and beaches.
-
C.
Baron de Kock
Baron de Kock is the Dutch noble title held by Hendrik Merkus de Kock, a 19th-century general and colonial administrator in the Dutch East Indies.
-
D.
Cronjé
Cronjé is an Afrikaans surname of French Huguenot origin, notably borne by figures such as Boer general Piet Cronjé.
-
E.
Verwoerd
Verwoerd is a surname most prominently associated with Hendrik Verwoerd, the South African prime minister widely regarded as the chief architect of apartheid.
- 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: de Heer Triple: [Rolf de Heer, familyName, de Heer]
Generated description
de Heer is a Dutch-origin surname borne by various notable individuals, including Australian film director Rolf de Heer.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: de Heer Target entity description: de Heer is a Dutch-origin surname borne by various notable individuals, including Australian film director Rolf de Heer.
-
A.
De Wit
De Wit is a Dutch surname commonly borne by individuals of Dutch origin and often associated with historical figures from the Netherlands.
-
B.
De Haan
De Haan is a seaside resort town on the Belgian coast, known for its Belle Époque architecture and beaches.
-
C.
Baron de Kock
Baron de Kock is the Dutch noble title held by Hendrik Merkus de Kock, a 19th-century general and colonial administrator in the Dutch East Indies.
-
D.
Cronjé
Cronjé is an Afrikaans surname of French Huguenot origin, notably borne by figures such as Boer general Piet Cronjé.
-
E.
Verwoerd
Verwoerd is a surname most prominently associated with Hendrik Verwoerd, the South African prime minister widely regarded as the chief architect of apartheid.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54fc9fa6c81909e1b988bdfb5ebcc |
completed | April 19, 2026, 9:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a050d822f0c8190988c9116cb7e3788 |
completed | May 13, 2026, 11:47 p.m. |
| NEDg | Description generation | batch_6a0512c6433c81908d3d82f330276c2a |
completed | May 14, 2026, 12:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05146f88cc8190bd2c91b966e24725 |
completed | May 14, 2026, 12:16 a.m. |
Created at: April 10, 2026, 11:47 a.m.