Triple
T13243209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sura Academy |
E315331
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Abba Arika |
E1028246
|
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: Abba Arika | Statement: [Sura Academy, foundedBy, Abba Arika]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abba Arika Context triple: [Sura Academy, foundedBy, Abba Arika]
-
A.
Abba Arika
chosen
Abba Arika, commonly known as Rav, was a leading third-century Babylonian amora and a foundational figure in the development of the Babylonian Talmud.
-
B.
Alonei Abba
Alonei Abba is a small rural community in northern Israel known for its historic Templer and German Protestant architecture and surrounding oak woodlands.
-
C.
Ariam
Ariam is a town located in the Ikwuano local government area of Abia State in southeastern Nigeria.
-
D.
Mika
Mika is a British-Lebanese pop singer-songwriter known for his flamboyant style and hit singles like "Grace Kelly."
-
E.
Fayruz
Fayruz is an alternate name for Abu Lu’lu’a Firuz, the Persian artisan historically known for assassinating the second Rashidun caliph, Umar ibn al-Khattab.
- 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d5b06148190a44e698bbe5cd529 |
completed | April 10, 2026, 11:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a38d09881909e8e3c32e9b1746e |
completed | May 3, 2026, 8:41 a.m. |
Created at: April 9, 2026, 9:23 p.m.