Triple
T20791469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bilthoven |
E511786
|
entity |
| Predicate | hasNotablePerson |
P304
|
FINISHED |
| Object |
Erica Terpstra
Erica Terpstra is a Dutch former Olympic swimmer, politician for the VVD, and longtime president of the Dutch Olympic Committee*Dutch Sports Federation.
|
E1451125
|
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: Erica Terpstra | Statement: [Bilthoven, hasNotablePerson, Erica Terpstra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erica Terpstra Context triple: [Bilthoven, hasNotablePerson, Erica Terpstra]
-
A.
Erika van Thiel
Erika van Thiel is best known as the wife of Dutch trance DJ and record producer Armin van Buuren.
-
B.
Nicole de Boer
Nicole de Boer is a Canadian actress best known for playing Ezri Dax on the television series Star Trek: Deep Space Nine.
-
C.
Denise van der Garde
Denise van der Garde is known as the wife of Dutch racing driver Giedo van der Garde and is a public figure occasionally seen in the international motorsport scene.
-
D.
Maayke Velders
Maayke Velders is known primarily as the spouse of Dutch naval hero Michiel de Ruyter.
-
E.
Angela Groothuizen
Angela Groothuizen is a Dutch singer, television presenter, and talent show judge known for her long career in music and Dutch TV entertainment.
- 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: Erica Terpstra Triple: [Bilthoven, hasNotablePerson, Erica Terpstra]
Generated description
Erica Terpstra is a Dutch former Olympic swimmer, politician for the VVD, and longtime president of the Dutch Olympic Committee*Dutch Sports Federation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Erica Terpstra Target entity description: Erica Terpstra is a Dutch former Olympic swimmer, politician for the VVD, and longtime president of the Dutch Olympic Committee*Dutch Sports Federation.
-
A.
Erika van Thiel
Erika van Thiel is best known as the wife of Dutch trance DJ and record producer Armin van Buuren.
-
B.
Nicole de Boer
Nicole de Boer is a Canadian actress best known for playing Ezri Dax on the television series Star Trek: Deep Space Nine.
-
C.
Denise van der Garde
Denise van der Garde is known as the wife of Dutch racing driver Giedo van der Garde and is a public figure occasionally seen in the international motorsport scene.
-
D.
Maayke Velders
Maayke Velders is known primarily as the spouse of Dutch naval hero Michiel de Ruyter.
-
E.
Angela Groothuizen
Angela Groothuizen is a Dutch singer, television presenter, and talent show judge known for her long career in music and Dutch TV entertainment.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2910d488190bc4be37512effc86 |
completed | April 21, 2026, 12:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08f8bc76508190b65a105fcd4decd1 |
completed | May 16, 2026, 11:07 p.m. |
| NEDg | Description generation | batch_6a08f9c9314c81909052d1a2e93d740a |
completed | May 16, 2026, 11:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08fa7040d88190b592d4f46249c2c1 |
completed | May 16, 2026, 11:14 p.m. |
Created at: April 16, 2026, 12:38 p.m.