Triple
T7405262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senhadja de Srair language |
E170853
|
entity |
| Predicate | ethnicGroup |
P194
|
FINISHED |
| Object |
Senhadja de Srair
Senhadja de Srair are an Amazigh (Berber) ethnic group from the Rif region of northern Morocco, traditionally associated with the Senhadja de Srair language.
|
E662349
|
NE FINISHED |
How this triple was built (4 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: Senhadja de Srair | Statement: [Senhadja de Srair language, ethnicGroup, Senhadja de Srair]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Senhadja de Srair Context triple: [Senhadja de Srair language, ethnicGroup, Senhadja de Srair]
-
A.
Masaesyli
Masaesyli was an ancient Berber kingdom in North Africa that preceded and formed part of what later became Numidia.
-
B.
Maïssade
Maïssade is a commune and town in Haiti known for its agricultural activities and location within the country’s central plateau region.
-
C.
Sa'ir
Sa'ir is a Palestinian town located in the southern West Bank, northeast of Hebron.
-
D.
Sirak Goryan
Sirak Goryan is a lesser-known pseudonym used by Armenian-American writer and playwright William Saroyan.
-
E.
Sand Saref
Sand Saref is a seductive and morally ambiguous femme fatale from the comic-book-inspired film "The Spirit," known for her complex past with the titular hero and her pursuit of priceless artifacts.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Senhadja de Srair Triple: [Senhadja de Srair language, ethnicGroup, Senhadja de Srair]
Generated description
Senhadja de Srair are an Amazigh (Berber) ethnic group from the Rif region of northern Morocco, traditionally associated with the Senhadja de Srair language.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Senhadja de Srair Target entity description: Senhadja de Srair are an Amazigh (Berber) ethnic group from the Rif region of northern Morocco, traditionally associated with the Senhadja de Srair language.
-
A.
Masaesyli
Masaesyli was an ancient Berber kingdom in North Africa that preceded and formed part of what later became Numidia.
-
B.
Maïssade
Maïssade is a commune and town in Haiti known for its agricultural activities and location within the country’s central plateau region.
-
C.
Sa'ir
Sa'ir is a Palestinian town located in the southern West Bank, northeast of Hebron.
-
D.
Sirak Goryan
Sirak Goryan is a lesser-known pseudonym used by Armenian-American writer and playwright William Saroyan.
-
E.
Sand Saref
Sand Saref is a seductive and morally ambiguous femme fatale from the comic-book-inspired film "The Spirit," known for her complex past with the titular hero and her pursuit of priceless artifacts.
- F. None of above. chosen
Provenance (5 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_69c68a6010108190925e5284de022660 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f271f1d481909a46d50b13b51a62 |
completed | March 27, 2026, 9:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8111540f08190919bc9d9670f5ef2 |
completed | March 28, 2026, 5:34 p.m. |
| NEDg | Description generation | batch_69c811c9c5e48190a610d890780c7aa4 |
completed | March 28, 2026, 5:37 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8128e49948190822787e76b1663a6 |
completed | March 28, 2026, 5:40 p.m. |
Created at: March 27, 2026, 3:10 p.m.