Triple
T18925832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mafra |
E462967
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Tournai |
—
|
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: Tournai | Statement: [Mafra, hasTwinTown, Tournai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tournai Context triple: [Mafra, hasTwinTown, Tournai]
-
A.
Tournai
chosen
Tournai is a historic city in western Belgium, known for its medieval architecture, including a UNESCO-listed cathedral and belfry, and its strategic importance in European conflicts.
-
B.
Courtrai
Courtrai, known today as Kortrijk, is a historic city in western Belgium noted for its medieval architecture and role in several significant European conflicts.
-
C.
Tournaisien
Tournaisien is a regional variety of the Picard language traditionally spoken in and around the city of Tournai in Belgium.
-
D.
Melincourt
Melincourt is a small locality in Wales known for its scenic surroundings, including the nearby Melincourt Brook and waterfall.
-
E.
Gadancourt
Gadancourt is a small commune in the Val-d'Oise department in the Île-de-France region of northern France.
- 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c9b94e008190a0e9a70aaf6d18ed |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 10, 2026, 11:59 a.m.