Triple
T21503052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dirk Nannes |
E530526
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Dirk Peter Nannes |
—
|
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: Dirk Peter Nannes | Statement: [Dirk Nannes, fullName, Dirk Peter Nannes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dirk Peter Nannes Context triple: [Dirk Nannes, fullName, Dirk Peter Nannes]
-
A.
Dirk Nannes
chosen
Dirk Nannes is a former Dutch-Australian fast bowler known for his successful Twenty20 career and for representing both the Netherlands and Australia in international cricket.
-
B.
Dirk Sanders
Dirk Sanders is an actor known for appearing in Jean-Luc Godard’s influential 1965 French New Wave film "Pierrot le Fou."
-
C.
Dirk Weissenborn
Dirk Weissenborn is a computer vision and machine learning researcher known for co-introducing the Vision Transformer (ViT) architecture.
-
D.
Steffen Groth
Steffen Groth is a German actor and director known for his roles in television series and films.
-
E.
Dirk De Jong
Dirk De Jong is a central character in Edna Ferber’s novel "So Big," known as the idealistic son whose artistic ambitions and personal choices contrast with his mother’s hard-won, practical values.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea5deb388190a89a1f94285b7e55 |
completed | April 23, 2026, 9:46 a.m. |
Created at: April 16, 2026, 6:24 p.m.