Triple
T4974552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KPMG |
E111733
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Piet Klijnveld
Piet Klijnveld was a Dutch accountant and entrepreneur who co-founded the international professional services firm that later became part of KPMG.
|
E496447
|
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: Piet Klijnveld | Statement: [KPMG, foundedBy, Piet Klijnveld]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piet Klijnveld Context triple: [KPMG, foundedBy, Piet Klijnveld]
-
A.
Piet Keizer
Piet Keizer was a renowned Dutch footballer, best known as a skillful left winger for Ajax and the Netherlands national team during the late 1960s and early 1970s.
-
B.
Piet de Jong
Piet de Jong was a Dutch politician who served as Prime Minister of the Netherlands from 1967 to 1971.
-
C.
Piet Kraak
Piet Kraak was a Dutch football goalkeeper who played for the Netherlands national team in the mid-20th century.
-
D.
Hans van Heeswijk
Hans van Heeswijk is a Dutch architect known for designing prominent cultural buildings, including major expansions and renovations of museums in the Netherlands.
-
E.
Piet Roozenburg
Piet Roozenburg was a renowned Dutch draughts (checkers) player and world champion, known for his significant contributions to the game’s theory and strategy.
- 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: Piet Klijnveld Triple: [KPMG, foundedBy, Piet Klijnveld]
Generated description
Piet Klijnveld was a Dutch accountant and entrepreneur who co-founded the international professional services firm that later became part of KPMG.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Piet Klijnveld Target entity description: Piet Klijnveld was a Dutch accountant and entrepreneur who co-founded the international professional services firm that later became part of KPMG.
-
A.
Piet Keizer
Piet Keizer was a renowned Dutch footballer, best known as a skillful left winger for Ajax and the Netherlands national team during the late 1960s and early 1970s.
-
B.
Piet de Jong
Piet de Jong was a Dutch politician who served as Prime Minister of the Netherlands from 1967 to 1971.
-
C.
Piet Kraak
Piet Kraak was a Dutch football goalkeeper who played for the Netherlands national team in the mid-20th century.
-
D.
Hans van Heeswijk
Hans van Heeswijk is a Dutch architect known for designing prominent cultural buildings, including major expansions and renovations of museums in the Netherlands.
-
E.
Piet Roozenburg
Piet Roozenburg was a renowned Dutch draughts (checkers) player and world champion, known for his significant contributions to the game’s theory and strategy.
- 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_69bd441a0eb481908050fa4273b19eae |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd722e77208190833dc760a57428d5 |
completed | March 20, 2026, 4:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bec34a07c0819089953ebcbe9cc3ff |
completed | March 21, 2026, 4:11 p.m. |
| NEDg | Description generation | batch_69bec505a5dc81908f79c1ade107c4ce |
completed | March 21, 2026, 4:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bec654fc4881909bf5458cdafc7ffd |
completed | March 21, 2026, 4:24 p.m. |
Created at: March 20, 2026, 1:33 p.m.