Triple
T10093866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | قسما |
E215812
|
entity |
| Predicate | يرمز إلى |
P63266
|
FINISHED |
| Object | تضحيات الشهداء الجزائريين |
—
|
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: تضحيات الشهداء الجزائريين | Statement: [قسما, يرمز إلى, تضحيات الشهداء الجزائريين]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: يرمز إلى Context triple: [قسما, يرمز إلى, تضحيات الشهداء الجزائريين]
-
A.
refersToAction
Indicates that one entity explicitly points to, mentions, or designates a specific action or event.
-
B.
oftenRefersTo
Indicates that one entity is frequently used to mention, denote, or reference another entity in common usage or context.
-
C.
to
Indicates a directional or goal-oriented relationship in which something is directed, transferred, or oriented toward a target or endpoint.
-
D.
euphemisticReferenceTo
Indicates that one expression is used as a milder or less direct way of referring to another, often to soften or obscure its impact.
-
E.
alsoRefersTo
chosen
Indicates that one term, label, or identifier is used as an alternative designation for the same entity or concept as 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_69ca83a4947c8190823a7495dc5d96ed |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd05da3688190b7a1ac8a58e5488f |
completed | April 2, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9b853c8190a2af993ce9b21309 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:01 p.m.