Triple
T11110502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welkenraedt |
E262741
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Herve |
E263276
|
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: Herve | Statement: [Welkenraedt, sharesBorderWith, Herve]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herve Context triple: [Welkenraedt, sharesBorderWith, Herve]
-
A.
Herve
chosen
Herve is a municipality in the province of Liège in Wallonia, eastern Belgium, known for its rural landscape and traditional Herve cheese.
-
B.
Denis of Paris
Denis of Paris is a 3rd-century Christian martyr and bishop, venerated as the patron saint of Paris and traditionally regarded as one of the city’s earliest evangelizers.
-
C.
Lemaire
Lemaire is a French surname borne by various notable figures in fields such as sports, politics, and the arts.
-
D.
Kenzo
Kenzo is a Japanese masculine given name borne by various notable figures in fields such as architecture, fashion, and entertainment.
-
E.
Lanvin
Lanvin is a historic French luxury fashion house, founded in 1889 by Jeanne Lanvin, renowned for its elegant haute couture and ready-to-wear collections.
- 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_69d6aa9b46cc8190b19f9f0cc45bf322 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a6964508190b679303d3b3a4fd6 |
completed | April 9, 2026, 12:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e42d759bc88190b670c373f3647a41 |
completed | April 19, 2026, 1:18 a.m. |
Created at: April 8, 2026, 9:27 p.m.