Triple
T19075379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIELE examinations |
E466888
|
entity |
| Predicate | certificateContent |
P134230
|
FINISHED |
| Object | overall Spanish level |
—
|
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: overall Spanish level | Statement: [SIELE examinations, certificateContent, overall Spanish level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: certificateContent Context triple: [SIELE examinations, certificateContent, overall Spanish level]
-
A.
certificate
Indicates that an entity has been formally recognized or authorized through an official certificate associated with another entity or qualification.
-
B.
certificateType
Indicates the specific kind or category of certificate associated with an entity or relationship.
-
C.
certificateIssued
Indicates that an official certificate has been formally created and granted by an issuing authority to a recipient or for a specific subject.
-
D.
certificateStatus
Indicates the current validity or state (e.g., valid, expired, revoked) of a certificate within a given system or context.
-
E.
certificateRating
Indicates the quality or approval level assigned to a certificate, typically reflecting its trustworthiness or compliance with certain standards.
- F. None of above. chosen
Provenance (4 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_69d8dd04f4488190b1121cc53ef2bfd6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e2e3c7b08190bf6448ead11ba916 |
completed | April 20, 2026, 8:25 a.m. |
| PD | Predicate disambiguation | batch_69e4b99f602881909eeb9c780597e0e6 |
completed | April 19, 2026, 11:16 a.m. |
| PDg | Predicate description generation | batch_69e4bfe8a06081909fd5c28a33e9f218 |
completed | April 19, 2026, 11:43 a.m. |
Created at: April 10, 2026, 12:04 p.m.