Triple
T7128790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue de la Loi |
E166132
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Parc Leopold |
E221014
|
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: Parc Leopold | Statement: [Rue de la Loi, near, Parc Leopold]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parc Leopold Context triple: [Rue de la Loi, near, Parc Leopold]
-
A.
Leopold Park
Leopold Park is a public green space and leisure park in the Belgian coastal city of Ostend, known for its landscaped gardens, ponds, and recreational facilities.
-
B.
Leopold Park
chosen
Leopold Park is a historic public park in Brussels known for its landscaped gardens, ponds, and proximity to major European Union institutions.
-
C.
Heckscher Park
Heckscher Park is a historic public park in Huntington, New York, known for its scenic pond, cultural events, and the Heckscher Museum of Art located on its grounds.
-
D.
Goffertpark
Goffertpark is a large public park in Nijmegen, Netherlands, known for its expansive green spaces, recreational facilities, and as a venue for major concerts and events.
-
E.
Rockefeller Park
Rockefeller Park is a waterfront green space in Lower Manhattan’s Battery Park City featuring lawns, gardens, public art, and views of the Hudson River.
- 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_69c6888350588190870cd552b427a1cd |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e66b230c819090ddbc5396868305 |
completed | March 27, 2026, 8:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7a33bf244819096db1351ebf62413 |
completed | March 28, 2026, 9:45 a.m. |
Created at: March 27, 2026, 2:44 p.m.