Triple
T6804473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herstal |
E156268
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Seraing |
E295664
|
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: Seraing | Statement: [Herstal, hasTwinTown, Seraing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seraing Context triple: [Herstal, hasTwinTown, Seraing]
-
A.
Seraing
chosen
Seraing is an industrial city in eastern Belgium known for its steelmaking heritage and location along the Meuse River near Liège.
-
B.
Overijse
Overijse is a municipality in the Flemish Brabant province of Belgium, known for its green residential character and extensive vineyards.
-
C.
Tongeren
Tongeren is a historic city in eastern Belgium, known as the country’s oldest town and for its well-preserved Roman and medieval heritage.
-
D.
Kanegem
Kanegem is a small village in West Flanders, Belgium, known for its historic church and rural character.
-
E.
Geervliet
Geervliet is a small historic town in the western Netherlands, located in the province of South Holland.
- 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_69c68826e6a48190a3d220b541e639de |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2ea459c819095388218d53c250a |
completed | March 27, 2026, 6:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71a9da0ac8190878799d4780f9b28 |
completed | March 28, 2026, 12:02 a.m. |
Created at: March 27, 2026, 2:16 p.m.