Triple
T31795046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabethan Poor Laws |
E811571
|
entity |
| Predicate | definesSystem |
P61905
|
FINISHED |
| Object | parish-based poor relief system |
—
|
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: parish-based poor relief system | Statement: [Elizabethan Poor Laws, definesSystem, parish-based poor relief system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: definesSystem Context triple: [Elizabethan Poor Laws, definesSystem, parish-based poor relief system]
-
A.
definesSystemAs
chosen
Indicates that one entity explicitly specifies or establishes another entity as the system to be used, referenced, or treated as authoritative.
-
B.
modelsSystemsWith
Indicates that one entity creates or uses a representation or abstraction to describe, analyze, or simulate another system.
-
C.
addsSystem
Indicates that one entity incorporates or installs a system into another entity or environment.
-
D.
packageSystem
Indicates a relationship where an item or component is organized, bundled, or managed within a particular packaging or distribution system.
-
E.
coversSystem
Indicates that one entity provides coverage, applicability, or protection for a particular system.
- 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_69f348e60748819082dcaa7792659803 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 30, 2026, 11:40 p.m.