Triple
T37684722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Statue of Jan van Nassau |
E938333
|
entity |
| Predicate | subjectHasRelation |
P33476
|
FINISHED |
| Object | brother of William of Orange |
—
|
LITERAL 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: brother of William of Orange | Statement: [Statue of Jan van Nassau, subjectHasRelation, brother of William of Orange]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectHasRelation Context triple: [Statue of Jan van Nassau, subjectHasRelation, brother of William of Orange]
-
A.
hasRelation
chosen
Indicates that there exists some specified relationship or association between two entities.
-
B.
subjectRelation
Indicates that one entity stands in a specified relational role or connection to another entity.
-
C.
hasRelationships
Indicates that an entity is connected to one or more other entities through specified types of relationships.
-
D.
testsRelation
Indicates a relationship where one entity evaluates, examines, or verifies another entity, typically to assess its properties, behavior, or correctness.
-
E.
supportsRelation
Indicates that one entity provides assistance, endorsement, or structural backing to another entity or its activity.
- 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_69f76ed881408190bc62a969530a4a53 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fde5d7d9548190880a9d95b8f0f66b |
completed | May 8, 2026, 1:32 p.m. |
| PD | Predicate disambiguation | batch_69fde4e1bf9c81909754545275eccc03 |
completed | May 8, 2026, 1:28 p.m. |
Created at: May 3, 2026, 4:18 p.m.