Triple
T28099416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Workers' Party of Belgium |
E710188
|
entity |
| Predicate | fullNameDutch |
P13254
|
FINISHED |
| Object | Partij van de Arbeid van België |
—
|
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: Partij van de Arbeid van België | Statement: [Workers' Party of Belgium, fullNameDutch, Partij van de Arbeid van België]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fullNameDutch Context triple: [Workers' Party of Belgium, fullNameDutch, Partij van de Arbeid van België]
-
A.
hasNameInDutch
chosen
Indicates that an entity is associated with a specific name or label expressed in the Dutch language.
-
B.
hasNameInMiddleDutch
Indicates that an entity is associated with a specific name as it appears in the Middle Dutch language.
-
C.
isEquivalentSurnameInDutch
Indicates that two surnames are equivalent or correspond to each other in their Dutch form or usage.
-
D.
hasLaterDutchName
Indicates that an entity was known by a different Dutch name at a later time than its original or earlier Dutch name.
-
E.
WestFrisianName
Indicates that the associated name is the form used in the West Frisian language for the given entity.
- F. None of above.
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_69ef9b70fd108190a875953b2e50ca91 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f640908b208190857b085879e60e1c |
completed | May 2, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9:04 p.m.