Triple
T10114916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Education (Administrative Provisions) Act 1907 |
E218332
|
entity |
| Predicate | introducedMedicalInspection |
P513
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Education (Administrative Provisions) Act 1907, introducedMedicalInspection, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducedMedicalInspection Context triple: [Education (Administrative Provisions) Act 1907, introducedMedicalInspection, true]
-
A.
examinedIn
Indicates that one entity is analyzed, inspected, or studied within the context, scope, or setting provided by another entity.
-
B.
introduced
chosen
Indicates that one entity caused another entity to become known, presented, or brought into use for the first time to a person, group, or context.
-
C.
isInspected
Indicates that an entity is examined or checked by another entity to assess its condition, quality, or compliance.
-
D.
firstTestedBy
Indicates that an item, concept, or process was initially tested or tried out by a particular agent or entity.
-
E.
medicalEvent
Indicates that a specific health-related occurrence or clinical incident has taken place involving one or more entities.
- 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_69ca83da93fc8190b54e44bc2b34857c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd161831c81908bb3c77caa7c3ce1 |
completed | April 2, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:04 p.m.