Triple
T24752218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zuiderzee |
E619174
|
entity |
| Predicate | separationStructure |
P153154
|
FINISHED |
| Object | Afsluitdijk |
—
|
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: Afsluitdijk | Statement: [Zuiderzee, separationStructure, Afsluitdijk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: separationStructure Context triple: [Zuiderzee, separationStructure, Afsluitdijk]
-
A.
typeOfSeparation
Indicates the specific manner or category of separation that exists or occurred between entities.
-
B.
separationSystem
chosen
Indicates a system or mechanism designed to separate or divide components, substances, or entities from one another.
-
C.
segmentStructure
Indicates that one entity represents a structural or organizational subdivision (a segment) within the overall structure of another entity.
-
D.
separatedIn
Indicates that two or more entities, once together or associated, have been divided, split, or otherwise placed into distinct parts, groups, or locations.
-
E.
separationMethod
Indicates the technique or process used to separate one substance, component, or entity from another.
- 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_69e2fabb349881908a13a212a0221a63 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f410a25ab88190a72db43043c1f6ff |
completed | May 1, 2026, 2:32 a.m. |
| PD | Predicate disambiguation | batch_69f40ef612c88190ab2f3f08d4a92018 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 4:25 a.m.