Triple
T31341228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saudi Research and Marketing Group |
E799310
|
entity |
| Predicate | notableNewspaper |
P55471
|
FINISHED |
| Object | Asharq Al-Awsat |
E702763
|
NE 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: Asharq Al-Awsat | Statement: [Saudi Research and Marketing Group, notableNewspaper, Asharq Al-Awsat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableNewspaper Context triple: [Saudi Research and Marketing Group, notableNewspaper, Asharq Al-Awsat]
-
A.
notableMagazine
Indicates that a person or entity is notably associated with a particular magazine, such as by being featured in, writing for, or significantly contributing to it.
-
B.
notableJournal
Indicates that the subject is a journal that is recognized as notable or significant in some relevant context.
-
C.
newspaperTitle
Indicates the title or name by which a newspaper is identified.
-
D.
notableReportingOn
Indicates that one entity has produced significant or widely recognized reporting, coverage, or journalistic work about another entity.
-
E.
publishedNewspaper
chosen
Indicates that an entity produced and issued a newspaper for public distribution.
- F. None of above.
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_69f224e51614819083141459a080e97c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2ad22c465481908e7fc6a7b67c5b41 |
completed | June 11, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_6a0379e5174c8190a0bdde7e381b7624 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 9:17 p.m.