Triple
T35060455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | معركة هرمجدون |
E1011576
|
entity |
| Predicate | تُفهم_في |
P83329
|
FINISHED |
| Object | بعض التفسيرات الحرفية |
—
|
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: بعض التفسيرات الحرفية | Statement: [معركة هرمجدون, تُفهم_في, بعض التفسيرات الحرفية]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: تُفهم_في Context triple: [معركة هرمجدون, تُفهم_في, بعض التفسيرات الحرفية]
-
A.
understands
Indicates that one entity comprehends, grasps the meaning of, or correctly interprets information, ideas, or expressions associated with another entity.
-
B.
comprende
Indicates that one entity includes, contains, or encompasses another as a part or component.
-
C.
canBeUnderstoodBy
chosen
Indicates that something is comprehensible or interpretable to a particular entity or group.
-
D.
betterUnderstoodAs
Indicates that one concept, term, or representation is more accurately or clearly interpreted when viewed as another specified concept, term, or representation.
-
E.
peutComprendre
Indicates that an entity has the ability or capacity to understand another entity or concept.
- 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_69f76dd09c308190a523454853ce842b |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7860a1154819088c0faac06bc3852 |
completed | May 3, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69f7841812f081909d878955d114088e |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4:01 p.m.