Triple
T1590700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cornelis Tromp |
E34171
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Cornelis Tromp |
E30015
|
NE FINISHED |
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: Cornelis Tromp | Statement: [Cornelis Tromp, name, Cornelis Tromp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cornelis Tromp Context triple: [Cornelis Tromp, name, Cornelis Tromp]
-
A.
Cornelis Tromp
chosen
Cornelis Tromp was a prominent 17th-century Dutch admiral renowned for his leadership in major naval battles during the Anglo-Dutch Wars.
-
B.
Maarten Tromp
Maarten Tromp was a renowned 17th-century Dutch admiral of the Eighty Years' War and the First Anglo-Dutch War, celebrated for his major naval victories against Spain and England.
-
C.
Ludolf Bakhuizen
Ludolf Bakhuizen was a prominent 17th-century Dutch Golden Age painter renowned for his dramatic marine scenes and seascapes.
-
D.
Reinier de Graaf
Reinier de Graaf was a 17th-century Dutch physician and anatomist renowned for his pioneering research on the female reproductive system and the discovery of ovarian follicles (now called Graafian follicles).
-
E.
Dirck van Delen
Dirck van Delen was a Dutch Golden Age painter renowned for his meticulously rendered architectural and church interior scenes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa621526e8819097d8c5330e527ed3 |
completed | March 6, 2026, 5:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad46a0f5348190ae3fe8033360d800 |
completed | March 8, 2026, 9:51 a.m. |
Created at: March 4, 2026, 7:27 p.m.