Triple
T8002775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cornelis de Vos |
E186290
|
entity |
| Predicate | workLocation |
P7
|
FINISHED |
| Object | Antwerp |
E32042
|
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: Antwerp | Statement: [Cornelis de Vos, workLocation, Antwerp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Antwerp Context triple: [Cornelis de Vos, workLocation, Antwerp]
-
A.
Antwerp
chosen
Antwerp is a major Belgian port city on the River Scheldt, renowned as a global center for the diamond trade and its historic Flemish art and architecture.
-
B.
Ghent
Ghent is a small unincorporated community and ski-area destination located in Raleigh County, West Virginia, United States.
-
C.
Ghent
Ghent is a historic city in the Flemish region of Belgium, known for its medieval architecture, canals, and role as a major cultural and economic center in the Middle Ages.
-
D.
Tervuren
Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
-
E.
Leuven
Leuven is a historic Belgian city known for hosting KU Leuven, one of Europe’s leading research universities, and for its vibrant academic and cultural life.
- 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_69ca82aaaf24819084b94d18f699ba53 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3cf2918081909ee0afab11caed63 |
completed | March 31, 2026, 3:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63bf5efc8190aa5cdc6707adbf71 |
completed | April 1, 2026, 12:15 a.m. |
Created at: March 30, 2026, 5:18 p.m.