Triple
T19320962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret II of Flanders |
E483221
|
entity |
| Predicate | placeOfDeath |
P21
|
FINISHED |
| Object | Ghent |
—
|
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: Ghent | Statement: [Margaret II of Flanders, placeOfDeath, Ghent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ghent Context triple: [Margaret II of Flanders, placeOfDeath, Ghent]
-
A.
Ghent
chosen
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.
-
B.
Ghent
Ghent is a small unincorporated community and ski-area destination located in Raleigh County, West Virginia, United States.
-
C.
Antwerp
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.
-
D.
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.
-
E.
Tervuren
Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
- 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e60d88951081909f7ce6e0610c7258 |
completed | April 20, 2026, 11:27 a.m. |
Created at: April 10, 2026, 1:32 p.m.