Triple
T31842703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | أحمد قريع |
E812848
|
entity |
| Predicate | نشاط بارز في |
P129177
|
FINISHED |
| Object | عملية السلام في الشرق الأوسط |
—
|
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: عملية السلام في الشرق الأوسط | Statement: [أحمد قريع, نشاط بارز في, عملية السلام في الشرق الأوسط]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: نشاط بارز في Context triple: [أحمد قريع, نشاط بارز في, عملية السلام في الشرق الأوسط]
-
A.
notableActivityIn
chosen
Indicates that an entity is particularly recognized for performing a significant activity within a specified place, context, or domain.
-
B.
majorActivity
Indicates that the related entity performs, participates in, or is primarily associated with a main or most significant activity.
-
C.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
D.
has activity
Indicates that one entity performs, exhibits, or is engaged in a particular action, behavior, or process associated with another entity.
-
E.
activityType
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
- 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_69f348eb327881909b4584b925742f6e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6affd8080819087c66792146c4056 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:49 p.m.