Triple
T16057330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saadi dynasty |
E389517
|
entity |
| Predicate | ethnicOrigin |
P194
|
FINISHED |
| Object | Arab |
E5830
|
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: Arab | Statement: [Saadi dynasty, ethnicOrigin, Arab]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arab Context triple: [Saadi dynasty, ethnicOrigin, Arab]
-
A.
Arabs
chosen
Arabs are a diverse ethnolinguistic group originating from the Arabian Peninsula and surrounding regions, united primarily by the Arabic language and a shared cultural and historical heritage.
-
B.
The Arab
"The Arab" is a 1924 American silent drama film, directed by Rex Ingram and starring Alice Terry, adapted from a stage play about a noble Arab patriot in wartime.
-
C.
Arabist
An Arabist is a scholar who specializes in the Arabic language, literature, history, and culture, often focusing on the broader Arab world and its civilizations.
-
D.
Arab world
The Arab world is a culturally and linguistically connected region of Arabic-speaking countries spanning North Africa and Western Asia.
-
E.
Arabic
Arabic is a Semitic language widely spoken across the Arab world and used as a liturgical language in Islam.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1837579488190964ca004c2eb01c4 |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbe678fc8190b36737a9cd29691c |
completed | May 10, 2026, 1:14 a.m. |
Created at: April 10, 2026, 4:57 a.m.